Speech Pitch

In this episode we share information about Sydney, Interspeech 2026 host city. You will learn you can travel from the airport to the conference venue itself, what to pack for your trip, the food culture, fun activities and some survival Aussie expressions.

Hosts: Pascal Hecker, Mohammed Mosuily

Guest: Monica Gonzalez Machorro

Script: Spyretta Leivaditi

Post production editors: Vishwas Shetty, Belu Ticona, Wei Xue, Snigdha Banik, Tiānyì Zhao

Here are the chapter mark time stamps:

00:00:00 - Intro

00:00:28 - Introduction Monica

00:02:19 - The long journey and jet lag

00:02:56 - Australia: a continent, and the Gadigal people

00:03:21 - Fun facts: green and gold, and the capital

00:04:19 - Architecture and landmarks

00:05:15 - View Points

00:06:05 - Emerald City: Sydney and New South Wales

00:07:00 -  Language and accents

00:08:37 - Currence and payment

00:09:29 - Safety

00:10:27 - Wildlife

00:16:30 - What to wear and sun protection

00:17:49 - What to pack

00:18:48 - Survival Information

00:23:35 - Food

00:30:10 - Souvenirs

00:30:45 - Fun activities and beaches

00:31:21 - Public transport: the Sunday cap and the Blue Mountains

00:32:31 - Survival Aussie slang

00:34:16 - See you all in Sydney!

00:34:44 - Outro

Ever wondered what it really takes to run a global association like ISCA, year after year? In this episode we sat down with Emmanuelle Foxonet – ISCA’s Office Manager and Administrative Coordinator – to uncover the people, processes, and stories behind the scenes.

‼️ What makes this episode extra special?

🗣️ Emmanuelle spoke in her native French, and we used ASR, translator, and TTS to create an English version of her voice – keeping her natural tone and personality while making the conversation accessible to our global community.

Hosts:Kay Berkling, Paige Tutossi

Post-Production:Pascal Hecker, Mohammed Mosuily, Wei Sue, Tianyi Zhao, Nikhil Raghav, Belu Ticona, Spyretta Leivaditi

00:00:45 - Introduction of Emmanuel Foxonet
00:02:02 - Challenges and Rewards of Office Management
00:03:05 - Evolution of the Office Manager Role
00:05:16 - Impactful Projects and Tasks
00:07:27 - Administrative Challenges in International Associations
00:08:52 - Future Tools for Efficiency
00:10:22 - Managing a Growing Community
00:11:33 - Behind-the-Scenes of Interspeech
00:15:39 - Funny Behind-the-Scenes Stories
00:19:09 - Logistical Hurdles in Diverse Locations
00:21:19 - Upcoming Conferences and Personal Experiences
00:22:57 - Surprising Changes in Research Culture
00:24:03 - Conclusion and Future Insights
00:24:58 - Outro

Join us as we sit down with Hynek and Morgan to talk all things speech research. We’re getting into the real stuff: why they started, whether they actually had a "grand plan" or were just following their curiosity, and how they decide which projects are actually worth the effort.

We also get into the technical weeds (in a good way) on things like energy efficiency and the battle between neural nets and knowledge-driven models. Plus, there’s plenty of solid advice for students on finding mentors, dealing with those brutal paper rejections, and knowing when to move fast versus taking it slow.

0:00:00 - intro
00:00:11 - introduction of the guests
00:01:16 - Hynek
00:02:02 - Morgan
00:04:08 - research focus: why did they get into speech research?
00:08:46 - did they have a plan on how to influence the field?
00:11:29 - were they able to fake that they had a grand goal when they were rather driven by curiosity?
00:19:13 - how do they chose the projects to pursue?
00:24:09 - what things did they pick up from working and collaborating with other people?
00:27:32 - what interdisciplinary knowledge is so important right now to drive the next big innovation forward?
00:34:36 - how to improve current neural nets; end-to-end vs. knowledge-driven approaches; energy efficiency
00:48:53 - mentoring: how can students approach seniors?
00:56:02 - moving fast and breaking things vs. moving slowly
00:58:04 - mentoring students
01:08:24 - how to deal with reviewers and rejections?
01:15:40 - what are they doing nowadays?
01:25:08 - question from the previous guests: pivotal moment in your career
01:31:15 - question for the next guest: will better deep neural networks solve everything speech related? How can we convince students to write papers on why they did their research?
01:32:35 - farewell
01:33:10 - outro

Jhansi shares her unique dual perspective—firstly as a researcher pushing boundaries in the field, and secondly as a member of the PhD panel, where she helped guide the next generation of scientists.

Host: Spyretta Leivaditi

Post-Production: Mohammed Mosuily, Pascal Hecker, Spyretta Leivaditi

Yuanyuan joins us to talk about her research in inclusive speech technology and the power of representation in AI. Whether she’s collecting personalized audio-video datasets or organizing the next big Interspeech, Yan is a champion for community.

Tune in for a candid conversation about:

Diverse Data: Accented, child, and disaster-related speech.

Leadership: Transitioning from workshop participant to organizer.

The PhD Mindset: Overcoming stress and prioritizing mental health.

Host: Spyretta Leivaditi

Post-Production: Mohammed Mosuily, Pascal Hecker

Fresh from the Young Female Researchers in Speech Workshop (YFRSW) 2025, Chin-Jou Li joins us to share her experience as a rising voice in the field. Chin-Jou discusses her poster presentation "Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages", her reflections on the mentoring and community at the workshop.

Host: Spyretta Leiavditi

Post-Production: Mohammed Mosuily, Pascal Hecker

Julian Zaidi and Marc-André Carbonneauarediscussing the practical differences between academic speech research and industrial application within the video game sector. The guests compare the Speech Synthesis Workshop to the broader Interspeech conference, noting that smaller venues allow for more technical discussions on voice cloning and evaluation metrics. They highlight critical challenges for the industry, such as maintaining speaker identity across varied emotions and the necessity for compact models that run efficiently on local hardware. The conversation further explores the cultural shift required when moving to a commercial environment, where consistent reliability and effective communication with non-experts are prioritised over theoretical novelty. Ultimately, the speakers emphasise that while academia thrives on exploration, industry demands functional, high-performance tools that meet the strict expectations of players.

Host: Paige Tuttösi

Post-Production: Zhengjun Yue, Pascal Hecker

We travel to the Speech Synthesis Workshop (SSW) 2025 to sit down with Xin Wang, Project Associate Professor at the National Institute of Informatics (NII) in Japan. Xin shares insights into his groundbreaking work. We also explore the highlights of this year's workshop and the evolving landscape of synthetic media.

Host: Paige Tuttösi

Post-Production: Tianyi Zhao, Pascal Hecker

Kick off the Speech Synthesis Workshop 2026 with an opening message from Matt Coler. In this introductory segment, Matt sets the stage for a year of breakthrough research, collaborative innovation, and the evolving landscape of synthetic speech. Whether you’re a veteran researcher or a curious newcomer, the journey starts here.

Host: Matt Coler

Post-Production: Zhengjun Yue, Pascal Hecker

From strangers to champions! 🏆 Meet Yassine Tijani and Joas Walraven, two young innovators who crossed paths at the Speech Science Festival and decided to team up on the spot. Tune in to hear how they dominated the Hackathon, what sparked their interest in speech tech, and the story behind their winning collaboration.

Host: Pascal Hecker

Post-Production: Pascal Hecker

Live from the Speech Science Festival! 🎤 We sat down with the University of Waterloo’s Nada Gohider and her wonderful children to get an inside look at this year's festivities. From hands-on events to the science of sound, they’re sharing their favorite moments and the unique energy that makes this festival a must-attend for families and researchers alike.

Host: Pascal Hecker

Post-Production: Pascal Hecker

Your memories, composed. 🎹 Paul Raingeard de la Blétière is bridging the gap between technology and nostalgia. This demo showcases his innovative robot that listens to life stories and transforms them into fully-realized songs. From chosen instruments to lyric-matching memories, it’s a personalized symphony for the soul, specifically crafted for the dementia community.

Host: Janice Huang

Post-Production: Wei Xue, Pascal Hecker

We introduce three innovators pushing the boundaries of speech tech in a fast-paced "Science Slam" format.

Aruna Srivastava (Univ. of Washington/Coal Labs): How movie clips can help you master any accent.

Jashu (Groningen University): The journey from China to the Netherlands to master the art of Singing Voice Synthesis.

Randy (TU Delft): Protecting your identity through adversarial attacks against unauthorized voice cloning. Three voices, three breakthroughs, one festival.

Host: Pascal Hecker

Post-Production: Paige Tuttösi, Pascal Hecker

In this kickoff episode, we head to the vibrant city of Rotterdam for the Speech Science Festival 2025. Your host and festival organizer, Ingo, sets the stage for an incredible gathering of researchers, linguists, and tech innovators.

Host: Ingo Siegert

Post-Production: Pascal Hecker

Roger Moore Professor of Spoken Language Processing who received the ISCA Medal for his contributions to spoken language processing join Speech Pitch podcast one more time having a fun and refreshing discussion with us.

Host: Paige Tuttösí

Post-production: Snigdha Banik

Meet Sebastian Bayerl, Professor at Rosenheim Technical University of Applied Sciences sharing his experince with us.

Host: Pascal Hecker

Post-production: Zhengjun Yue, Pascal Hecker

Meet Louis ten Bosch, Senior Researcher Radboud University and Technical committee lead in Interspeech 2025, who shares his background and giving us insights on Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers . A paper that he co-authored with TY Zhong, E Janse, C Tejedor-Garcia, M Larson.

Host: Spyretta Leivaditi

Post-production: Pascal Hecker, Spyretta Leivaditi

Meet Denise Dipersio Associate Director at Linguistic Data Consortium sharing her experience with us.

Host: Pascal Hecker

Post-production: Wei Xue

Meet Xiyuan Gao, PhD candidate in University of Groningen campus Fryslan, and focuses on pragmatic language understanding in Human-Machine-Interaction (HMI), with an emphasis on how multimodal cues.

Host: Spyretta Leivaditi

Post-production: Pascal Hecker

Meet Janine Rugayan software developer in Gintel AS sharing her experience wih us.

Host: Pascal Hecker

Post-production: Mohammed Mosuily

Meet Chin Kum Wai Manager in innovation and partnerships of Klass, a company that constantly focuses in innovating to produce software and hardware solutions that enhance public safety.

Host: Pascal Hecker

Post-production: Zhengjun Yue, Pascal Hecker

Meet Signe Gram Sand, MSc student in Aarhus Universitet and winner of Best poster award of Young Female Reseacher in Speech workshop.

Host: Spyretta Leivaditi

Post-production: Pascal Hecker

Meet Yaroslav Getman, PhD Candidate at Aalto University, specializing in self-supervised speech representation learning and its applications in automatic speech recognition (ASR) and speech technology for underrepresented languages.

Host: Priyanshi Pal

Post-production: Wenxi Fei

Meet Takayuki Arai Professor in Sophia University with research interest in Speech Communication, Acoustics, Acoustic Phonetics, Speech Processing for People with Communication Disorders. He was a part of Show and Tell

Host: Paige Tuttösí

Post-production: Snigdha Banik

Meet Catarina Bolteho PostDoctoral researcher in INESC-ID and one of the original hosts of Speech Pitch this time as a guest.

Host: Pascal Hecker

Post-production: Wenxi Fei

Meet Björn Professor of Health Informatics at TUM and Chi-Chun (Jeremy) Lee Professor at National Tsing Hua University.

Host: Pascal Hecker

Post-production: Wei Xue

Meet Robin Netzorg PhD researcher at UC Berkeley and Juliana Francis PhD researcher in KTH Royal Institute of Technology.

Host: Paige Tuttösí

Post-production: Snigdha Banik

On Monday 18th and Tuesday 19th

Meet us in Ahoy Center at Dock 17

From 09.00 – 11.00 and from 14.00 – 17.00

Overall 105 mentees and 40 mentors registered, will meet us on 19th of August 2025, during Interspeech 2025.

This is the highest participation EVER!!

Round table event

Location:Foyer 2.2

Time: 12:00 pm - 1:30pm

One-on-one mentoring is up to the participants availability during Interspeech.

Meet us on 21st of August 2025

Location: room Port 1B

Time:12:00pm - 1:30 pm

Registration Form:https://docs.google.com/forms/d/e/1FAIpQLScUo0xDH5la8yjr9B4TWYrw3lRwsyTfR7wqwOpDu-_cCqn2sg/viewform

Mentors: Felix Burkhardt(audEERING GmbH, Germany), Ting Dang(University of Melbourne, Australia), José González-López(University of Granada, Spain), Catherine Lai(Universita of Edinburgh, Scotland)

In this episode we share information about Rotterdam, the host city of Interspeech 2025. You will learn how you can travel from the airport to the conference venue itself, what to pack for this trip, the food culture of Netherlands, fun activities and some survival Dutch.

Listen to:

Hosts: Pascal Hecker, Spyretta Leivaditi, Wei Xue

Guest Host:Marjolein van Os

Editors: Pascal Hecker, Spyretta Leivaditi, Mohammed Mosuily, Paige Tuttösí, Snigdha Banik, Wenxi Fei

0:00:00 - Intro

00:00:32 - Introduction Marjolein

00:01:23 - Rotterdam

00:03:22 - View Points and Architecture

00:07:11 - Sightseeing: Cube Houses

00:08:24 - Sightseeing: Markthal

00:09:04 - Other cities in the Netherlands

00:10:17 - Nicknames of buildings

00:11:23 - Survival Information: language

00:12:07 - Survival Information: currency and public transportation

00:14:25 - Survival Information: safety, red light district

00:17:04 - Survival Information: the weather

00:19:17 - Survival Information: what to pack

00:21:54 - Survival Information: how to get to the Interspeech venue

00:23:52 - Survival Information: trains

00:25:50 - Survival information: accommodation

00:27:47 - Food

00:33:01 - Customs in restaurants

00:39:55 - Desserts and candies

00:41:12 - Souvenirs

00:45:26 - Other cities to visit

00:50:53 - Windmills in the Netherlands

00:52:41 - Survival Dutch

00:53:31 - Emergency numbers

00:54:26 - See you all in Rotterdam!

00:55:02 - Outro

In this episode, Georgia Maniati, a Speech Scientist specializing in Text-to-Speech, shares her career path. She recounts her evolution from a linguist to a speech scientist, detailing her experiences in Greece, Edinburgh, and Italy, and how these shaped her current role. Georgia also discusses the current hurdles in text-to-speech technology, particularly for low-resource languages such as Greek.

00:00:11 - intro

00:00:49- Georgia's vita

00:10:20 - Fellowships for young researchers

00:17:04- Georgia's role at Samsung

00:21:31 - hard skills in her position

00:26:47 - recent, exciting projects she worked on

00:31:22 - challenges in developing synthetic voices

00:33:41 - Greek is a low-resource language, which challenges does it imply?

00:34:38 - naturalness of TTS

00:39:03 - mentoring and volunteering activities

00:43:37 - young female researchers in speech

00:45:20 - science communication for non expert audiences  

0:53:32 - gender bias in TTS

00:53:37 - current blind spots in industry

00:56:08 - biggest challenges in her journey

00:59:38 - biggest motivation at work and what's next

01:01:11 - what did she wish to know earlier in her career?

01:02:33 - the question from Titouan Parcollet

01:03:49 - her question for the next guest

01:04:19 - outro

The most long-awaited episode of 2025, the mental health episode is here.

In this episode the Speech Pitch team asked your question to Jasmina Bakic, who is a scientific researcher and psychologist in a psychology practice person-centered in Amsterdam. You will hear 3 stories from our audience and Jasmina's responses to them and to the many questions related to burn out, self doubt, toxic enviroments, self-harm, ADHD and how to seek for help.

Hosts: Priyanshi Pal, Spyretta Leivaditi, Orchid Chetia Phukan, Sarthak Jain

Editors: Pascal Hecker, Snigdha Banik, Spyretta Leivaditi, Kalliopi Kakamouka

0:00:00 intro

0:00:x introducing Jasmina and her areas of interest at work

0:04:52 first story: burn out

0:15:35 potential way outs for burnout

0:17:50 second story: depression upon entering a PhD

0:23:15 should you share mental health concerns with your supervisor?

0:25:25 if your advisor is not empathetic, how should you get help instead?

0:27:55 third story: how do I build effective relationships with my co-workers

0:37:50 how do you ensure better collaboration in the research effort?

0:43:42 short question section: how can one stay focused if your supervisor doesn't support you

0:47:30 how can one cope with toxic behaviour of people around you?

0:57:00 how do you know that resigning is the right decision?

1:00:49 how to get out of a phase of self-doubt?

1:04:56 what is a healthy way of self-worth?

1:11:28 Balance between competition and your own pace

1:14:57 fear of being judged to ask "stupid questions"

1:19:35 how can you react to unfruitful feedback?

1:22:02 how to overcome the feeling of not being sufficient

1:25:56 how to spot someone who might be considering self-harm

1:29:40 how to persuade someone to seek help

1:32:08 how can a supervisor grief after an unfortunate event

1:36:40 ADHD in adults

1:43:08 take-home-message

1:43:48 outro

This is the uncut version of our episode with Say IT Labs. We meet Lukas Latacz and Erich Reiter, founders of Say IT Labs, and discuss their career, the founding process of their company, and their contribution to pathological speech using their Artificial Intelligence (AI) applications.

Hosts: Pascal Hecker, Spyretta Leivaditi

Editors:Pascal Hecker, Snigdha Banik, Spyretta Leivaditi, Kay Berkling, Kalliopi Kakamouka, Mohammed Mosuily

0:00:00 - Intro

0:00:30 - Introducing Erich Reiter and Lukas Latacz

0:04:22 - The origin story of SAY IT Labs

0:05:56 - How Erich came to Belgium

0:07:33 - Challenges when founding the company

0:12:18 - How did they secure initial funding

0:15:00 - SAY IT Labs as a company

0:19:43 - The science of stuttering and the game stutter stars

0:26:10- How is it validated?

0:30:00 - Different languages

0:31:35 - Smart glasses for Parkinson's

0:38:30 - Advice for young entrepreneurs

0:47:20 - Work life balance

0:53:08 - Question from Titouan: What is your biggest challenge to overcome for your product to succeed?

0:56:44 - Question for the next guest: How to transition from monolingual to multilingual approaches?

0:57:06 - Support SAY IT Labs: interns

0:57:50: - Outro

In this episode we meet Lukas Latacz and Erich Reiter, founders of SAY IT Labs, and discuss their career, the founding process of their company, and their contribution to pathological speech using their Artificial Intelligence (AI) applications.

Hosts:Pascal Hecker, Spyretta Leivaditi

Editors:Pascal Hecker, Snigdha Banik, Spyretta Leivaditi, Kalliopi Kakamouka, Orchid Chetia Phukan, Sarthak Jain, Vishakha Choudhary

Titouan Parcollet is a “Research Scientist at the Samsung AI Center Cambridge” and an “adjunct researcher at the Cambridge Machine Learning Systems Lab from the University of Cambridge”. Further, he is an “Associate Professor on leave from the Laboratoire Informatique d'Avignon (LIA) and Avignon Université (FR)”. His current Research focus is on self-supervised / representation learning and on continual learning. He played an instrumental part in the development of SpeechBrain and Pytorch-Kaldi.

In this episode you will follow Titouan’s origin story, how he entered university, his PhD journey, his teaching approach and of course his current research topics.

Hosts:Spyretta Leivaditi, Pascal Hecker

Editors:Pascal Hecker, Janice Huang and Snigdha Banik

00:00:00 - Intro

00:00:20 - Welcoming Titouan Parcollet

00:01:01 - Titouan's entry into university and early career

00:05:48 - Titouan's PhD journey

00:15:33 - PhD exchange with the Mila institute

00:17:58 - Importance of a PhD advisor and how to chose your PhD position

00:27:50 - Titouan's teaching approach and experience

00:35:50 - His current research topic and his view on the field

00:40:42 - His view on academia and industry

00:43:26 - Work-life balance, mental health, burnout

00:54:34  -Imposter syndrome

01:03:07 - The SpeechBrain toolkit

01:16:06 - The Flower framework

01:17:55 - The E-SSL project: Efficient Self-Supervised Learning for Inclusive and Innovative Speech Technologies

01:22:51 - Titouan answer's Florian Eyben's question

01:24:41 - Titouan's question for the next guest

01:25:49 - Outro

Florian Eybenspearheads technology and innovation at audEERING, focusing on developing industry-leading products for speech emotion recognition and deep learning-based audio analysis. He earned my PhD in Computational Paralinguistics from TUM in Munich, Germany. He also specialize in deep learning, audio feature extraction, signal processing, project management, and tech innovation. He is the lead author of the openSMILE toolkit and a co-author of the GPU-accelerated LSTM-RNN training toolkit, CuRRENNT.

In this podcast episode, Florian shares his academic and professional journey, gives insights about openSMILE and of course shares how audEERING was founded.

Enjoy !!

Hosts: Pascal Hecker, Spyretta Leivaditi

Editors: Janice Huang and Pascal Hecker

Chapters:

00:00:00 Intro
00:00:26 Welcoming Florian Eyben
00:00:55 Florian's background and research journey
00:10:46 More about openSMILE
00:22:37 Founding audEERING and what it is
00:35:10 For young researchers
00:50:30 Encouragement from Florian
01:00:50 Fun questions
01:17:37 Outro

Meet Rob van Son, Senior researcher at the Netherlands Cancer Institute Amsterdam who shares his interests and his impressions on Interspeech 2024 in Kos.

Host: Zhengjun Yue

Meet Shrikanth Narayanan who is professor of Electrical and Computer Engineering and Niki & C. L. Max Nikias Chair in Engineering shares his research interests and his impressions on Interspeech 2024 in Kos.

Host: Orchid Chetia Phukan

Meet Shekhar Nayak, associate professor in Speech Technology in Campus Fryslân of University of Groningen. Listen about his interests, his academic journey and of course his impression on Interspeech 2024 in Kos.

Host: Spyretta Leivaditi

Siyang is a PhD student in KTH Royal Institute of Technology shares his experience and impression of Interspeech 2024 in Kos.

Host: Paige Tuttosi

Meet Suhas, Ph.D. candidate in Informatics at Penn State University, where he works at the intersection of Machine Learning, Human-Computer Interaction, and Health. He shares is interests and his impressions on Interspeech 2024.

Hosts: Spyretta Leivaditi

Esther Klabbers senior speech reseracher and CEO of Phaistos Speech & Language Technology Services, shares her research interests and het impressions on Interspeech 2024 in Kos.

Host: Spyretta Leivaditi

Meet Mathew Magimai Doss, Senior Researcher at Idiap Research Institute, shares his research interests and his impressions on Interspeech 2024 in Kos.

Host: Orchid Chetia Phukan 

Meet Iuliia, PhD Researcher at Universität des Saarlandes, sharing her research interests and impressions on Interspeech 2024 in Kos.

Host: Wei Xue

Meet Harm Lameris, PhD Student in Conversational AI in KTH Royal Institute of Technolog shares his interests and his impressions on Interspeech 2024 in Kos.

Host: Paige Tuttösí

Meet Thomas, PostDoctoral researcher in INESC-ID and one of the original hosts of Speech Pitch this time as a guest. Grab this opportunity to listen about his research interests interest and of course how did he exerince Interspeech 2024 in Kos.

Host: Wei Xue

Aaricia is a ASR Researcher & Computational Linguist at Alphaspeech, introduces her interests and impressions of Interspeech 2024.

Host: Spyretta Leivaditi

Marta won Best Poster Award 2024 in Young female Researchers in Speech Workshop (YFRSW 2024) and shares with us her research interests and her impressions of Interspeech 2024 in Kos.

Host: Sarthak Jain

In this episode we share information about the Greek island, Kos that is hosting Interspeech 2024. You will learn how you can travel from the airport to the conference venue itself, what to pack for this trip, the food culture of Greece, fun activities in the island and some survival Greek. To practise some survival Greek press here

In Travel Information.pdf you can find some traveling information to the venue.

Book in advance the shuttle service specially organized for Interspeech 2024 delegatesHERE.

Survival Greek:

Thank you , [efxaɾiˈsto]

You are welcome, [parakaˈlo]

Where is the toilet, [ˈpu ˈine i tuaˈleta]

Water, [neˈɾo]

Yes, [ˈne]

No, [ˈoçi]

Left, [aɾisteˈɾa]

Right, [ðeksiˈa]

Help, [voˈiθia]

Fire, [foˈtça]

Hotel, [ksenoðoˈçio]

Good morning, [kaliˈmeɾa]

Good afternoon,[kaliˈspera]

Good night, [kaliˈnixta]

Pharmacy,[faɾmaˈcio]

Hospital, [nosokoˈmio]

Hosts: Pascal Hecker, Spyretta Leivaditi

Editor: Spyretta Leivaditi

00:00:00 -Intro
00:00:22 -Outline
00:00:40 -About Kos
00:01:33 -Kos geography
00:03:47 -History
00:05:32 -Language, currency, payment
00:06:51 -Safety
00:07:58 -Taxis
00:08:40 -Weather
00:11:01 -What to pack
00:11:30 -Power adaptors
00:12:04 -Medicine and pharmacies
00:13:35 -How to get to the conference venue
00:15:31 -Buses
00:19:16 -Bus app for Kos "Kos near bus"
00:19:35 -Hotels
00:20:49 -Food
00:26:22 -Vegetarian food options
00:28:09 -Drinks
00:31:33 -Activities on Kos
00:36:49 -Beaches
00:39:15 -Travel destinations by ferry
00:40:30 -Greek words

Matt Coler is an accomplished academic and a leading figure in the field of Voice Technology. He is an Associate Professor of Language and Technology at the University of Groningen, Campus Fryslân. Notably, Matt initiated and now leads the Master’s Program in Voice Technology at the university, a testament to his dedication and expertise in the field. In addition to his teaching and research responsibilities, Matt also leads a summer school in Speech Tech at the University of Groningen, providing students with an immersive learning experience and a deeper understanding of speech technology.

In this podcast episode, Matt shares his unique journey from studying Philosophy and Mandarin Chinese in the U.S. to becoming a professor in Groningen. His research interests are diverse, but a common thread is his focus on under-resourced languages. Matt believes that academia has a crucial role in supplementing industry by addressing problems that may not be as lucrative but are nonetheless important. He provides an overview of the Master’s Program for Voice Technology, emphasising its practical applications and collaboration with industry. The program is designed to equip students with the skills and knowledge they need to make significant contributions to the field. Matt also discusses the Speech Tech Summer School, which explores a new topic each year, keeping the curriculum fresh and relevant. This approach reflects Matt’s commitment to staying at the forefront of advancements in speech technology.

Hosts: Wenxi Fei, Pascal Hecker

Editor: Spyretta Leiavditi

Chapters:

00:00:00-Intro

00:00:20-Welcoming Matt Coler

00:00:52-Matt's background

00:02:10-Matt's research journey to in Groningen

00:07:00-Matt's research areas

00:12:18-Assessing speech

00:18:13-Matt's stance on industry and academia

00:20:50-MSc Voice/Speech Technology at University of Groningen in Campus Fryslân

00:44:34-Speech tech Summer School

00:52:41-Ethical aspects in his research

00:57:34-Matt's take on work-life balance

01:03:00-Fun questions

01:11:14-Outro

There is no such thing as a banquet that lasts forever, and farewells can be bittersweet as we part ways with old and newfound friends from the conference. Yet, the real magic often happens behind the scenes.

In this episode, we were joined by two dedicated members of the UK Speech 2023 local committee: Hend TM Elghazaly and Olga Iakovenko. As the conference venue quieted down after attendees departed, they offered us a glimpse into the world of conference organisation as a team. From the joys they found in the process to the challenges they encountered, they shared their insights and experiences, leaving us with valuable advice for future student volunteers.

In this episode, we had the pleasure of interviewing three senior students from the Centre for Doctoral Training in Speech and Language Technologies, University of Sheffield: George Close, Mary Hewitt and Tom Pickard. Drawing from their personal experience, they shared valuable insights on how to navigate conferences without getting exhausted, along with recounting their most memorable and unexpected moments.

In this episode, we had the pleasure of speaking with Robbie Sutherland and Mattias Cross, two first-year PhD students from the University of Sheffield, working on speech and language technologies. With limited conference experience, they discussed their expectations for such events and posed insightful questions for seasoned senior students to shed light on.

UK Speech annually extends its invitation to local businesses, offering them a platform to showcase their advancements in speech technologies. In this exclusive interview, we had the pleasure of hosting representatives from Oxford Wave Research, a company specialising in audio and speech processing, voice biometrics, and deep learning-driven product development.

During our conversation with Dr Anil Alexander and Dr Finnian Kelly, we delved into the vast potential of speech technologies and their significance for everyday individuals. The discussion also touched upon the unique research dynamics within a smaller company and strategies for fostering collaboration with academic researchers. Last but not least, Anil and Finnian revealed the qualities they seek in potential new team members -- yes, they are hiring! Tune in to seize this opportunity!

Apart from big speech research groups, there are also many other research groups of various sizes. In this episode, we interviewed Dr. Jennifer Williams, an Associate Professor at the University of Southampton, who has worked a lot on privacy and security in the speech field. Joining us was Beatrice Pakenham-Walsh, a final-year undergraduate student. UK Speech 2023 marked Beatrice's conference debut, where she presented a poster on using audio analysis to detect pain.

In this episode, Dr. Williams and Beatrice shared their experiences and perspectives on doing speech research at the University of Southampton. We discussed the challenge of interdisciplinary work, the role of a research community and how individual researchers can use a community to identify potential collaborative opportunities. 

Apart from big speech research groups, there are also many other research groups of various sizes. In this episode, we interviewed Dr Zoe Handley, an Associate Professor at the Department of Education at the University of York. Dr Handley has more than 20 years of experience in applying speech technologies in language education. 

In the discussion, Dr Handley shared her views about the evolution of speech technologies from the perspective of language learning and teaching. She also talked about how to find collaborations outside the researcher’s institute, and how to leverage conferences such as UKSpeech to find such collaborations. At the end, we also discussed the connection between STEM (science, technology, engineering and maths) and social sciences, as well as applications in general.

The University of Cambridge has one of the biggest speech research groups in the UK. In this episode, we have Dr Kate Knill and her colleague Dr Mengjie Qian from the Machine Intelligence Laboratory at the University of Cambridge. Dr Knill is a Principal Research Associate in the Machine Intelligence Laboratory. She is also one of the keynote speakers at UK Speech 2023. Her speech is titled ‘Foundation Models in Spoken Language Processing: Time to go home or make hay?

In this episode, Dr Knill recapped her keynote speech with the key line for the audience to take away. Together with Dr Qian, she also shared her opinions about the big changes in automated language teaching and assessment over the past few years, as well as what it will be like in the next 5 to 10 years. We also discussed the potential to apply such automotive assessment techniques in the music field. In the end, they shared their vision about the UK and Ireland Speech 2024, which will be held at the University of Cambridge.

This episode is the first in a special series of mini-episodes covering the UK Speech 2023 Conference. In preparation for the conference, we have ISCA-SAC’s volunteer Guanyu Huang talk to Dr Anton Ragni, the Local Committee Chair of the conference, about its organisation, history, and impact of the conference on the speech research community in the UK.

In this episode, we have a conversation with Roger K. Moore, Professor of Spoken Language Processing at the University of Sheffield. Prof. Moore has more than 50 years' experience in research and development of speech technology, having been President of the European/International Speech Communication Association from 1997 to 2001, and the Head of the UK Government's Speech Research Unit from 1985 to 1999.

During this conversation, Prof. Moore spoke to us about the development of the field of speech technology in the last 40 years, and shared his views on the past and future of the field, as well as on the possible impacts of Large Language Models in speech technology . We further discussed his own work on speech recognition and animal vocalisations, and got to learn about his experience as a professor and his love for photography.

In this episode, we have Professor Pascale Fung with us. Pascale is the Chair Professor at the Department of Electronic & Computer Engineering at The Hong Kong University of Science & Technology (HKUST), a visiting professor at the Central Academy of Fine Arts in Beijing, and the Director of HKUST Centre for AI Research (CAiRE). Apart from her highly-achieved academic roles, she is also very active in the industry.

In our conversation, Pascale generously shared her experiences and knowledge regarding the relationship between AI and art, why and how we need to work on empathetic machines, the uncanny valley effect in conversational agents, global collaboration on ethical AI, as well as her personal role models and interesting stories and enlightening insights about science communication.

In this episode, we are chatting with John Hansen, a Professor at the University of Texas at Dallas. He is also the founder of the Center for Robust Speech Systems at the same university, and was the president of ISCA – the International Speech Communication Association, until last year. John has worked in many different fields, so we had the opportunity to discuss many interesting topics, including robust and speech recognition, health applications of speech technologies, and even got to hear really interesting stories about NASA, within the context of the fearless steps project. This is a long episode, but full on incredible stories and interesting perspectives on science, and the speech community.

In this episode, we are chatting with Shri Narayanan,a Professor at the University of Southern California. Among many other things, Shri is a Fellow of many institutions including the National Academy of Inventors (NAI), IEEE, and ISCA; an editor of several journals, including the Computer, Speech and Language Journal; and (Spoiler Alert!!) a musician of South Indian Classical Variety. We talk about multidisciplinary research, the importance of being heard, and the big challenges that motivate Shri in speech research. We also discuss ways of making an impact, through publication and entrepreneurial aspects.

In this episode, we are chatting with Nicholas Cummins, a Lecturer in AI for speech analysis at King's College London. We talk about speech technologies for health-related applications with a special focus on mental health. We also discuss several of Nick's recent projects as well as his views and advices on living abroad.

In this episode we are chatting with Odette Scharenborg, an Associate Professor and Delft Technology Fellow. She is also a member of the ISCA board, where she acts as the chair of the diversity committee, co-chair of the Interspeech Conferences committee and of the Technical Committee. We talk about diversity concerns not only in speech technology but also within the community. Odette also told us about her career, its highlights as well as its least successful aspects.

This is the first episode of Speech Pitch, ISCA-SAC's (Student Advisory Committee of the International Speech Communication Association) new podcast. We are interviewing Iona Gessinger, last year’s ISCA-SAC General Coordinator and winner of the best student-paper award in Interspeech 2020.