Google at Interspeech 2023 – Google Analysis Weblog

This week, the twenty fourth Annual Conference of the International Speech Communication Association (INTERSPEECH 2023) is being held in Dublin, Eire, representing one of many world’s most intensive conferences on analysis and expertise of spoken language understanding and processing. Specialists in speech-related analysis fields collect to participate in oral displays and poster periods and to construct collaborations throughout the globe.

We’re excited to be a Platinum Sponsor of INTERSPEECH 2023, the place we might be showcasing greater than 20 analysis publications and supporting quite a few workshops and particular periods. We welcome in-person attendees to drop by the Google Analysis sales space to fulfill our researchers and take part in Q&As and demonstrations of a few of our newest speech applied sciences, which assist to enhance accessibility and supply comfort in communication for billions of customers. As well as, on-line attendees are inspired to go to our virtual booth in Topia the place you will get up-to-date info on analysis and alternatives at Google. Go to the @GoogleAI Twitter account to seek out out about Google sales space actions (e.g., demos and Q&A periods). You can even be taught extra in regards to the Google analysis being introduced at INTERSPEECH 2023 under (Google affiliations in daring).

Board and Organizing Committee

ISCA Board, Technical Committee Chair: Bhuvana Ramabhadran

Space Chairs embrace:     Evaluation of Speech and Audio Indicators: Richard Rose    Speech Synthesis and Spoken Language Era: Rob Clark    Particular Areas: Tara Sainath

Satellite tv for pc occasions

Keynote speak – ISCA Medalist

Survey Speak

Speech Compression within the AI PeriodSpeaker: Jan Skoglund

Particular session papers

Cascaded Encoders for Fine-Tuning ASR Models on Overlapped SpeechRichard Rose, Oscar Chang, Olivier Siohan

TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and RecognitionHakan Erdogan, Scott Knowledge, Xuankai Chang*, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey

Papers

DeePMOS: Deep Posterior Mean-Opinion-Score of SpeechXinyu Liang, Fredrik Cumlin, Christian Schüldt, Saikat Chatterjee

O-1: Self-Training with Oracle and 1-Best HypothesisMurali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Kartik Audhkhasi

Re-investigating the Efficient Transfer Learning of Speech Foundation Model Using Feature Fusion MethodsZhouyuan Huo, Khe Chai Sim, Dongseong Hwang, Tsendsuren Munkhdalai, Tara N. Sainath, Pedro Moreno

MOS vs. AB: Evaluating Text-to-Speech Systems Reliably Using Clustered Standard ErrorsJoshua Camp, Tom Kenter, Lev Finkelstein, Rob Clark

LanSER: Language-Model Supported Speech Emotion RecognitionTaesik Gong, Josh Belanich, Krishna Somandepalli, Arsha Nagrani, Brian Eoff, Brendan Jou

Modular Domain Adaptation for Conformer-Based Streaming ASRQiujia Li, Bo Li, Dongseong Hwang, Tara N. Sainath, Pedro M. Mengibar

On Training a Neural Residual Acoustic Echo Suppressor for Improved ASRSankaran Panchapagesan, Turaj Zakizadeh Shabestary, Arun Narayanan

MD3: The Multi-dialect Dataset of DialoguesJacob Eisenstein, Vinodkumar Prabhakaran, Clara Rivera, Dorottya Demszky, Devyani Sharma

Dual-Mode NAM: Effective Top-K Context Injection for End-to-End ASRZelin Wu, Tsendsuren Munkhdalai, Pat Rondon, Golan Pundak, Khe Chai Sim, Christopher Li

Using Text Injection to Improve Recognition of Personal Identifiers in SpeechYochai Blau, Rohan Agrawal, Lior Madmony, Gary Wang, Andrew Rosenberg, Zhehuai Chen, Zorik Gekhman, Genady Beryozkin, Parisa Haghani, Bhuvana Ramabhadran

How to Estimate Model Transferability of Pre-trained Speech Models?Zih-Ching Chen, Chao-Han Huck Yang*, Bo Li, Yu Zhang, Nanxin Chen, Shuo-yiin Chang, Rohit Prabhavalkar, Hung-yi Lee, Tara N. Sainath

Improving Joint Speech-Text Representations Without AlignmentCal Peyser, Zhong Meng, Ke Hu, Rohit Prabhavalkar, Andrew Rosenberg, Tara N. Sainath, Michael Picheny, Kyunghyun Cho

Text Injection for Capitalization and Turn-Taking Prediction in Speech ModelsShaan Bijwadia, Shuo-yiin Chang, Weiran Wang, Zhong Meng, Hao Zhang, Tara N. Sainath

Streaming Parrotron for On-Device Speech-to-Speech ConversionOleg Rybakov, Fadi Biadsy, Xia Zhang, Liyang Jiang, Phoenix Meadowlark, Shivani Agrawal

Semantic Segmentation with Bidirectional Language Models Improves Long-Form ASRW. Ronny Huang, Hao Zhang, Shankar Kumar, Shuo-yiin Chang, Tara N. Sainath

Universal Automatic Phonetic Transcription into the International Phonetic AlphabetChihiro Taguchi, Yusuke Sakai, Parisa Haghani, David Chiang

Mixture-of-Expert Conformer for Streaming Multilingual ASRKe Hu, Bo Li, Tara N. Sainath, Yu Zhang, Francoise Beaufays

Real Time Spectrogram Inversion on Mobile PhoneOleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang, Xia Zhang, Fadi Biadsy

2-Bit Conformer Quantization for Automatic Speech RecognitionOleg Rybakov, Phoenix Meadowlark, Shaojin Ding, David Qiu, Jian Li, David Rim, Yanzhang He

LibriTTS-R: A Restored Multi-speaker Text-to-Speech CorpusYuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, Ankur Bapna

PronScribe: Highly Accurate Multimodal Phonemic Transcription from Speech and TextYang Yu, Matthew Perez*, Ankur Bapna, Fadi Haik, Siamak Tazari, Yu Zhang

Label Aware Speech Representation Learning for Language IdentificationShikhar Vashishth, Shikhar Bharadwaj, Sriram Ganapathy, Ankur Bapna, Min Ma, Wei Han, Vera Axelrod, Partha Talukdar

 * Work carried out whereas at Google

The post Google at Interspeech 2023 – Google Analysis Weblog appeared first on AIPressRoom.