University of Cambridge > Talks.cam > CUED Speech Group Seminars

CUED Speech Group Seminars

Add to your list(s) Send you e-mail reminders Further detail
Subscribe using ical/vcal (Help)

A series of talks taking place (normally) on Mondays 12-1pm for researchers working in speech technology, spoken language processing and related fields to present their work.

The aim of these talks is to promote communication and collaboration within the speech group and with other related research groups both in the University and outside.

Tell a friend about this list:

If you have a question about this list, please contact: Dr Kate Knill; Kimberly Cole; Simon Webster McKnight; el584. If you have a question about a specific talk, click on that talk to find its organiser.

0 upcoming talks and 111 talks in the archive.

What are the unsolved problems in Conversation Design?

Hybrid meeting. If you'd like to talk with Cathy after the talk over sandwiches please contact Kate Knill kmk1001@cam.ac.uk.

UserCathy Pearl, Google.

HouseHybrid: JDB Seminar Room, Engineering Department or Zoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYVlFwU2NDWGpmdz09.

ClockMonday 18 July 2022, 11:00-12:00

Confidence estimation for attention-based encoder-decoder models for speech recognition

This talk will be both online (zoom) and offline (CBL Meeting Room)

UserQiujia Li (University of Cambridge).

HouseZoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYVlFwU2NDWGpmdz09.

ClockMonday 06 June 2022, 12:00-13:00

Deciphering speech: a top-down approach to zero-resource speech recognition

This talk will be both online (zoom) and offline (JDB Seminar Room)

UserPeter Bell (University of Edinburgh).

HouseZoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYVlFwU2NDWGpmdz09.

ClockWednesday 01 June 2022, 15:00-16:00

SoundStream: An End-to-End Neural Audio Codec

This talk will be on zoom

UserNeil Zeghidour (Google).

HouseZoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYVlFwU2NDWGpmdz09.

ClockMonday 04 April 2022, 12:00-13:00

Machines that can read lips

This talk will be on zoom

UserPingchuan Ma (Imperial College London).

HouseZoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYVlFwU2NDWGpmdz09.

ClockMonday 25 October 2021, 12:00-13:00

Generative Speech Separation based on Pitch Information

This talk will be on zoom

UserDr Xiang Li, Cambridge University Engineering Department.

HouseZoom: https://us06web.zoom.us/j/87426783837?pwd=akx4ZWZMYVZML2ZoOWRlYzdRaTd6dz09.

ClockMonday 11 October 2021, 12:00-13:00

Time-domain multi-channel speech separation and extraction

This talk will be on zoom.

UserJisi Zhang, University of Sheffield.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 08 June 2021, 12:00-13:00

Long Sequence-to-Sequence Summarization: Efficient Transformer Models & Complementary Techniques

This talk will be on zoom.

UserPotsawee Manakul, Cambridge University Engineering Department.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 25 May 2021, 12:00-13:00

Audio-Visual Learning: Challenges and New Approaches

This talk will be on zoom

UserDr Jie Pu, Cambridge University Engineering Department.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 18 May 2021, 12:00-13:00

Automatic Assessment Systems for the Spoken CALL Shared Tasks

This talk will be held on zoom

UserMengjie Qian, Cambridge University Engineering Department.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 11 May 2021, 12:00-13:00

Combination of Deep Speaker Embeddings for Diarisation and Discriminative Neural Clustering for Speaker Diarisation

Seminar on zoom

UserBrian Sun, Quija Li, Florian Kreyssig, Cambridge University Speech Research Group.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 16 March 2021, 12:00-13:00

Natural Language Interpretation in Dialogue Systems

Seminar on zoom

UserDr Svetlana Stoyanchev, Speech Technology Group, Toshiba CRL.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 09 March 2021, 12:00-13:00

Interpretable representation learning for speech and audio signals

Seminar on zoom

UserDr Purvi Agrawal, Indian Institute of Science (IISc) and Microsoft India.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 02 March 2021, 12:00-13:00

Semi-supervised Learning for Low-resource Multilingual and Multimodal Speech Processing with Machine Speech Chain

Seminar on zoom

UserProf Sakriani Sakti, Nara Institute of Science and Technology (NAIST), Japan.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 23 February 2021, 12:00-13:00

Should Ensemble Members Be Calibrated?

Seminar on zoom

UserDr Xixin Wu, Cambridge University Engineering Department.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 16 February 2021, 12:00-13:00

Selection of Talks from Interspeech 2020

Seminar on zoom

UserYiting 'Edie' Lu, Vyas Raina, Qingyun Dou, Cambridge University Speech Research Group.

HouseZoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT2tDUT09.

ClockTuesday 26 January 2021, 12:00-13:00

Transformer: the 3rd generation neural network acoustic models for ASR and its application at Facebook

Please note change of time from original post to 3-4pm

UserYongqiang Wang, Facebook.

HouseZoom: https://zoom.us/j/94591123432?pwd=bUJObFZ3UnFYLy9pWENDcS9aYUZqUT09.

ClockMonday 30 November 2020, 15:00-16:00

Information Engineering Distinguished Lecture Series

Speech Recognition: What’s Left?

This talk is organised in conjunction with the IEEE Signal Processing Society for which Dr Michael Picheny is a Distinguished Industry Speaker

UserDr Michael Picheny.

HouseDepartment of Engineering - LT1.

ClockTuesday 12 November 2019, 12:00-13:00

Robust speech processing on multi-talker mixed speech

UserYanmin Qian, Shanghai Jiao Tong University.

HouseDepartment of Engineering - James Dyson Building Seminar Room.

ClockFriday 10 May 2019, 11:00-12:00

Predictive Uncertainty in Deep Learning

UserAndrey Malinin (University of Cambridge).

HouseDepartment of Engineering - LR5 Lecture Room.

ClockThursday 03 May 2018, 12:00-13:00

Structured Deep Learning for Dialogue Management

UserKai Yu, Shanghai Jiao Tong University.

HouseDepartment of Engineering - LR3B Lecture Room.

ClockMonday 19 February 2018, 12:00-13:00

Statistical Spoken Dialogue Systems and the Challenges for Machine Learning

UserProfessor Steve Young, Cambridge University Engineering Department.

HouseDepartment of Engineering - Lecture Theater 2 (Inglis Building).

ClockMonday 27 February 2017, 12:00-13:00

Very deep convolutional neural networks for speech recognition

UserTom Sercu, IBM Watson, USA.

HouseDepartment of Engineering - LR5.

ClockFriday 19 August 2016, 12:00-13:00

Don't multiply lightly: exploring how DNN depth interacts with HMM independence assumptions in hybrid HMM/DNN's used for ASR

UserSteven Wegmann, Semantic Machines and International Computer Science Institute (ICSI).

HouseJames Dyson Building Seminar Room - Department of Engineering.

ClockMonday 04 July 2016, 12:00-13:00

Towards Advanced Conversational Systems

UserG. Wu, Maluuba.

HouseDepartment of Engineering - LR11.

ClockWednesday 11 November 2015, 12:00-13:00

What the DNN heard? Dissecting the machine brain for a better insight.

User Khe Chai Sim, National University of Singapore.

HouseDepartment of Engineering - LR5.

ClockWednesday 04 November 2015, 12:00-13:00

Interspeech presentations

Sandwiches will be provided at 12:00

UserVarious (University of Cambridge).

HouseDepartment of Engineering - LR5.

ClockWednesday 02 September 2015, 11:00-13:00

ICASSP presentations

A sandwich lunch will be provided

UserVarious.

HouseDepartment of Engineering - LR4.

ClockThursday 09 April 2015, 12:00-14:00

Dynamic Topic Adaptation for Statistical Machine Translation

Sandwich lunch from 13:00

UserEva Hasler (University of Cambridge).

HouseDepartment of Engineering - LR5.

ClockFriday 06 March 2015, 13:30-14:30

The Geometry of Machine Translation

Sandwich lunch from 13:00

UserRory Waite (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 16 January 2015, 13:30-14:30

Cluster Adaptive Training for Deep Neural Networks

Sandwiches will be provided

UserTian Tan (visitor at CUED).

HouseDepartment of Engineering - LR10.

ClockFriday 28 November 2014, 12:00-13:00

Syllable based keyword search: transducing syllable lattices to word lattices

Sandwiches will be provided at 13:00

UserJim Hieronymus, ICSI (US).

HouseDepartment of Engineering - LT2.

ClockFriday 21 November 2014, 13:30-14:30

Modulation spectrum-based approach to high-quality statistical parametric speech synthesis

Sandwiches will be provided

UserShinnosuke Takamichi (NAIST, Japan).

HouseDepartment of Engineering - Oatley 1 Meeting Room.

ClockMonday 17 November 2014, 12:00-13:00

Interspeech presentations

UserVarious.

HouseDepartment of Engineering - LR6.

ClockWednesday 10 September 2014, 12:00-13:30

ICASSP presentations

UserVarious.

HouseDepartment of Engineering - LR6.

ClockFriday 25 April 2014, 12:00-13:00

Investigation of multilingual speech-to-text systems for use in spoken term detection

UserKate Knill (University of Cambridge) .

HouseDepartment of Engineering - LR12.

ClockThursday 03 April 2014, 12:00-13:00

Efficient Lattice Rescoring Using Recurrent Neural Network Language Models

UserXunying (Andrew) Liu (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 07 March 2014, 13:00-13:30

Will recurrent neural network language models scale?

UserTony Robinson (Cantab Research).

HouseDepartment of Engineering - LR6.

ClockFriday 07 March 2014, 12:00-13:00

Refinements in Hierarchical Phrase-Based Translation

UserJuan Pino (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 07 February 2014, 12:00-13:00

Physically Situated Spoken Language Interaction: Opportunities and Challenges

UserDan Bohus (Microsoft Research, Redmond).

HouseDepartment of Engineering - LR12.

ClockWednesday 30 October 2013, 12:30-13:30

Recurrent Continuous Translation Models

UserNal Kalchbrenner (University of Oxford).

HouseDepartment of Engineering - LR12.

ClockMonday 07 October 2013, 12:00-13:00

POMDP-based dialogue manager adaptation to extended domains

UserMilica Gasic (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 06 September 2013, 12:00-13:00

Interspeech practice session

UserVarious.

HouseDepartment of Engineering - LR6.

ClockFriday 02 August 2013, 12:00-13:30

Recent Work in Acoustic Modelling at Google

UserDr Andrew Senior, Google, New York.

HouseDepartment of Engineering - LR6.

ClockThursday 11 July 2013, 11:30-12:30

Dialog state tracking: Open problems, challenge task, and recent work

UserJason D. Williams, Microsoft Research.

HouseDepartment of Engineering - LR12.

ClockTuesday 11 June 2013, 12:00-13:00

ICASSP poster practice session

UserVarious.

HouseDepartment of Engineering - LR6.

ClockFriday 03 May 2013, 12:00-13:00

Introduction to Dialogue Systems

UserBlaise Thomson (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 15 March 2013, 11:30-13:00

Paraphrastic Language Models / Structured SVMs for ASR

UserAndrew Liu, Austin Zhang.

HouseDepartment of Engineering - LR12.

ClockFriday 01 February 2013, 13:00-14:00

Acoustic Factorisation for Robust Speech Recognition

UserEric(Yongqiang) Wang (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 11 January 2013, 12:30-13:30

Efficient Decoding with Generative Score-Spaces Using the Expectation Semiring

UserRogier van Dalen (University of Cambridge).

HouseDepartment of Engineering - LR6.

ClockFriday 30 November 2012, 12:30-13:30

Overview of Speech Technology Research at CUED

UserSpeaker to be confirmed.

HouseDepartment of Engineering - LR6.

ClockFriday 02 November 2012, 12:00-13:30

Machine Intelligence Lab Seminar

Spectral Moment Features for Robust Speech Recognition

UserPirros Tsiakoulis (Institute for Language and Speech Processing (ILSP)).

HouseCambridge University Engineering Department, Lecture Room 6.

ClockTuesday 31 May 2011, 13:00-14:00

speech synthesis seminar series

Speech Production Mechanism And Vocoding Technique In Statistical Parametric Speech Synthesis

Sandwich will be provided.

UserRanniery (Toshiba Research Europe Ltd.) and Yannis (Google).

HouseCambridge University Engineering Department, Lecture Room 2.

ClockWednesday 02 March 2011, 13:00-15:00

speech synthesis seminar series

New and emerging applications of 'adaptive' speech synthesis'

Sandwich will be provided.

UserJunichi Yamagishi, Centre for Speech Technology Research (CSTR) at the University of Edinburgh.

HouseCambridge University Engineering Department, Lecture Room 4.

ClockWednesday 09 February 2011, 13:00-15:00

speech synthesis seminar series

Modelling trajectories in statistical speech synthesis

This is the second talk of the speech synthesis seminar series.

UserMatt Shannon (Cambridge) and Heiga Zen (Toshiba Research Europe Ltd.).

House Cambridge University Engineering Department, Lecture Room 2.

ClockWednesday 26 January 2011, 13:00-15:00

speech synthesis seminar series

STATISTICAL SPEECH SYNTHESIS

UserHeiga Zen (Toshiba Research Europe Ltd.).

House Cambridge University Engineering Department, Lecture Room 4.

ClockTuesday 11 January 2011, 13:00-15:00

Machine Intelligence Laboratory Speech Seminars

Towards Tree-to-Tree Translation

UserDavid Chiang (University of Southern California).

HouseLR5, Engineering Department, Baker Building.

ClockMonday 01 February 2010, 13:00-14:00

Machine Intelligence Laboratory Speech Seminars

Bayesian Learning Approaches for Speech Recognition

UserProfessor Jen-Tzung Chien (National Cheng Kung University, Taiwan).

HouseLR5, Engineering Department, Baker Building.

ClockFriday 04 September 2009, 13:00-14:00

Machine Intelligence Laboratory Speech Seminars

Factors Affecting ASR Model Self-Training

UserScott Novotney (HLTCOE and BBN Technologies).

HouseLR5, Engineering Department, Baker Building.

ClockTuesday 01 September 2009, 11:00-12:00

Machine Intelligence Laboratory Speech Seminars

Dialectal Chinese Speech Recognition

UserThomas Fang Zheng (Tsinghua University, Beijing).

HouseLR5, Engineering Department, Baker Building.

ClockFriday 24 August 2007, 11:30-12:30

Machine Intelligence Laboratory Speech Seminars

Tracheoesophageal Speech Repair

UserArantza Del Pozo, CUED Machine Intelligence Laboratory.

HouseLR6, Engineering Department, Baker Building.

ClockMonday 20 November 2006, 13:00-14:00

Machine Intelligence Laboratory Speech Seminars

Use of Linguistic Information and Reordering Strategies for Ngram- based Statistical Machine Translation

UserAdria de Gispert, TALP Research Centre – Univ. Politecnica de Catalunya (UPC), Barcelona, Spain.

HouseLR5, Engineering Department, Baker Building.

ClockTuesday 31 October 2006, 13:00-14:00

Please see above for contact details for this list.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity