Interspeech 2023

1,141 papers

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer

Kyuhong Shim, Jinkyu Lee, Simyoung Chang, Kyuwoong Hwang

DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer

Goeric Huybrechts, Srikanth Ronanki, Xilai Li, Hadis Nosrati, Sravan Bodapati

Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation

Hanbyul Kim, Seunghyun Seo, Lukas Lee, Seolki Baek

ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs

Xingchen Song, Di Wu, Binbin Zhang, Zhendong Peng, Bo Dang

Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learning

Yuting Yang, Yuke Li, Binbin Du

Robust Keyword Spotting for Noisy Environments by Leveraging Speech Enhancement and Speech Presence Probability

Chouchang Yang, Yashas Malur Saidutta, Rakshith Sharma Srinivasa, Ching-Hua Lee, Yilin Shen

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data

Seunghan Yang, Byeonggeun Kim, Kyuhong Shim, Simyoung Chang

Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics

Umberto Michieli, Pablo Peso Parada, Mete Ozay

On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation

Gene-Ping Yang, Yue Gu, Qingming Tang, Dongsu Du, Yuzong Liu

Self-Paced Pattern Augmentation for Spoken Term Detection in Zero-Resource

Sudhakar P, Sreenivasa K. Rao, Pabitra Mitra

Matching Latent Encoding for Audio-Text based Keyword Spotting

Kumari Nishu, Minsik Cho, Devang Naik

Multimodal Speech Recognition for Language-Guided Embodied Agents

Allen Chang, Xiaoyuan Zhu, Aarav Monga, Seoho Ahn, Tejas Srinivasan

SparseVSR: Lightweight and Noise Robust Visual Speech Recognition

Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma, Alexandros Haliassos, Stavros Petridis

Streaming Audio-Visual Speech Recognition with Alignment Regularization

Pingchuan Ma, Niko Moritz, Stavros Petridis, Christian Fuegen, Maja Pantic

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

Zhifu Gao, Zerui Li, Jiaming Wang, Haoneng Luo, Xian Shi

A Novel Self-training Approach for Low-resource Speech Recognition

Satwinder Singh, Feng Hou, Ruili Wang

An Efficient and Noise-Robust Audiovisual Encoder for Audiovisual Speech Recognition

Zhengyang Li, Chenwei Liang, Timo Lohrenz, Marvin Sach, Björn Möller

Weakly supervised glottis segmentation in high-speed videoendoscopy using bounding box labels

Varun Belagali, Achuth Rao, Prasanta Kumar Ghosh

An Analysis of Glottal Features of Chronic Kidney Disease Speech and Its Application to CKD Detection

Jihyun Mun, Sunhee Kim, Myeong Ju Kim, Jiwon Ryu, Sejoong Kim

Glottal source analysis of voice deficits in basal ganglia dysfunction: evidence from de novo Parkinson's disease and Huntington's disease

Michal Novotný, Tereza Tykalová, Michal Šimek, Tomáš Kouba, Jan Rusz

Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling

Theodoros Kouzelis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros

Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation

Massa Baali, Ibrahim Almakky, Shady Shehata, Fakhri Karray

CNVVE: Dataset and Benchmark for Classifying Non-verbal Voice

Ramin Hedeshy, Raphael Menges, Steffen Staab

DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model

Helin Wang, Thomas Thebaud, Jesus Villalba, Myra Sydnor, Becky Lammers

Transfer Learning to Aid Dysarthria Severity Classification for Patients with Amyotrophic Lateral Sclerosis

Tanuka Bhattacharjee, Anjali Jayakumar, Yamini Belur, Atchayaram Nalini, Ravi Yadav

A Stutter Seldom Comes Alone – Cross-Corpus Stuttering Detection as a Multi-label Problem

Sebastian P. Bayerl, Dominik Wagner, Ilja Baumann, Florian Hönig, Tobias Bocklet

Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra

Zhengjun Yue, Erfan Loweimi, Zoran Cvetkovic

A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning

Jiyang Tang, William Chen, Xuankai Chang, Shinji Watanabe, Brian MacWhinney

Whisper Features for Dysarthric Severity-Level Classification

Siddharth Rathod, Monil Charola, Akshat Vora, Yash Jogi, Hemant A. Patil

Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features

Monica Gonzalez-Machorro, Pascal Hecker, Uwe D. Reichel, Helly N. Hammer, Robert Hoepner

Multimodal Locally Enhanced Transformer for Continuous Sign Language Recognition

Katerina Papadimitriou, Gerasimos Potamianos

Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test

Eungbeom Kim, Yunkee Chae, Jaeheon Sim, Kyogu Lee

Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target

Guan-Wei Wu, Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee

Investigating Pre-trained Audio Encoders in the Low-Resource Condition

Hao Yang, Jinming Zhao, Gholamreza Haffari, Ehsan Shareghi

Knowledge Distillation on Joint Task End-to-End Speech Translation

Khandokar Md. Nayem, Ran Xue, Ching-Yun Chang, Akshaya Vishnu Kudlu Shanbhogue

Spot Keywords From Very Noisy and Mixed Speech

Ying Shi, Dong Wang, Lantian Li, Jiqing Han, Shi Yin

Query Based Acoustic Summarization for Podcasts

Samantha Kotey, Rozenn Dahyot, Naomi Harte

Enc-Dec RNN Acoustic Word Embeddings learned via Pairwise Prediction

Adhiraj Banerjee, Vipul Arora

Large Dataset Generation of Synchronized Music Audio and Lyrics at Scale using Teacher-Student Paradigm

Cristian Chivriga, Rinita Roy

A Dual Attention-based Modality-Collaborative Fusion Network for Emotion Recognition

Xiaoheng Zhang, Yang Li

Combining language corpora in a Japanese electromagnetic articulography database for acoustic-to-articulatory inversion

Tianfang Yan, Kikuo Maekawa, Yukiko Nota, Masayuki Hirata

Speaker Tracking using Graph Attention Networks with Varying Duration Utterances across Multi-Channel Naturalistic Data: Fearless Steps Apollo-11 Audio Corpus

Meena M. C. Shekar, John H. L. Hansen

BASS: Block-wise Adaptation for Speech Summarization

Roshan Sharma, Siddhant Arora, Kenneth Zheng, Shinji Watanabe, Rita Singh

ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition

Yuanchao Li, Zeyu Zhao, Ondrej Klejch, Peter Bell, Catherine Lai

Pragmatic Pertinence: A Learnable Confidence Metric to Assess the Subjective Quality of LM-Generated Text

Jerome R. Bellegarda

Improving Under-Resourced Code-Switched Speech Recognition: Large Pre-trained Models or Architectural Interventions

Joshua Jansen van Vüren, Thomas Niesler

A Lexical-aware Non-autoregressive Transformer-based ASR Model

Chong-En Lin, Kuan-Yu Chen

Language-universal Phonetic Encoder for Low-resource Speech Recognition

Siyuan Feng, Ming Tu, Rui Xia, Chuanzeng Huang, Yuxuan Wang

A Binary Keyword Spotting System with Error-Diffusion Based Feature Binarization

Dingyi Wang, Mengjie Luo, Lin Li, Xiaoqin Wang, Shushan Qiao

Unsupervised Code-switched Text Generation from Parallel Text

Jie Chi, Brian Lu, Jason Eisner, Peter Bell, Preethi Jyothi

Confidence-based Ensembles of End-to-End Speech Recognition Models

Igor Gitman, Vitaly Lavrukhin, Aleksandr Laptev, Boris Ginsburg

Text Injection for Capitalization and Turn-Taking Prediction in Speech Models

Shaan Bijwadia, Shuo-Yiin Chang, Weiran Wang, Zhong Meng, Hao Zhang

SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings

Alexandra Antonova, Evelina Bakhturina, Boris Ginsburg

Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning

Xuankai Chang, Brian Yan, Yuya Fujita, Takashi Maekaku, Shinji Watanabe

Embedding Articulatory Constraints for Low-resource Speech Recognition Based on Large Pre-trained Model

Jaeyoung Lee, Masato Mimura, Tatsuya Kawahara

Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition

Wenxuan Wang, Guodong Ma, Yuke Li, Binbin Du

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition

Siyuan Feng, Ming Tu, Rui Xia, Chuanzeng Huang, Yuxuan Wang

Accelerating Transducers through Adjacent Token Merging

Yuang Li, Yu Wu, Jinyu Li, Shujie LIU

A Neural Time Alignment Module for End-to-End Automatic Speech Recognition

Dongcheng Jiang, Chao Zhang, Philip C. Woodland

Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition

Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe

Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation

Minglun Han, Feilong Chen, Jing Shi, Shuang Xu, Bo Xu

Leveraging Cross-Utterance Context For ASR Decoding

Robert Flynn, Anton Ragni

Improving Joint Speech-Text Representations Without Alignment

Cal Peyser, Zhong Meng, Rohit Prabhavalkar, Andrew Rosenberg, Tara Sainath

Blank Collapse: Compressing CTC Emission for the Faster Decoding

Minkyu Jung, Ohhyeok Kwon, Seunghyun Seo, Soonshin Seo

Language Model Personalization for Improved Touchscreen Typing

Jiban Adhikary, Keith Vertanen

Knowledge Distillation Approach for Efficient Internal Language Model Estimation

Zhipeng Chen, Haihua Xu, Yerbolat Khassanov, Yi He, Lu Lu

Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation

Jiaxu Zhu, Weinan Tong, Yaoxun Xu, Changhe Song, Zhiyong Wu

Delay-penalized CTC Implemented Based on Finite State Transducer

Zengwei Yao, Wei Kang, Fangjun Kuang, Liyong Guo, Xiaoyu Yang

Model-Internal Slot-triggered Biasing for Domain Expansion in Neural Transducer ASR Models

Yiting Lu, Philip Harding, Kanthashree Mysore Sathyendra, Sibo Tong, Xuandi Fu

Adapter-tuning with Effective Token-dependent Representation Shift for Automatic Speech Recognition

Dianwen Ng, Chong Zhang, Ruixi Zhang, Yukun Ma, Trung Hieu Nguyen

Adapting Multi-Lingual ASR Models for Handling Multiple Talkers

Chenda Li, Yao Qian, Zhuo Chen, Naoyuki Kanda, Dongmei Wang

MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition

Jiamin Xie, John H. L. Hansen

Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition

Xiaodong Cui, George Saon, Brian Kingsbury

Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino

Can Contextual Biasing Remain Effective with Whisper and GPT-2?

Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland

Exploring Sources of Racial Bias in Automatic Speech Recognition through the Lens of Rhythmic Variation

Li-Fang Lai, Nicole Holliday

CLRL-Tuning: A Novel Continual Learning Approach for Automatic Speech Recognition

Zhihan Wang, Feng Hou, Ruili Wang

SlothSpeech: Denial-of-service Attack Against Speech Recognition Models

Mirazul Haque, Rutvij Shah, Simin Chen, Berrak Sisman, Cong Liu

Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation

Ziyang Ma, Zhisheng Zheng, Guanrou Yang, Yu Wang, Chao Zhang

Effective Training of Attention-based Contextual Biasing Adapters with Synthetic Audio for Personalised ASR

Burin Naowarat, Philip Harding, Pasquale D'Alterio, Sibo Tong, Bashar Awwad Shiekh Hasan

Wave to Syntax: Probing spoken language models for syntax

Gaofei Shen, Afra Alishahi, Arianna Bisazza, Grzegorz Chrupała

Target Vocabulary Recognition Based on Multi-Task Learning with Decomposed Teacher Sequences

Aoi Ito, Tatsuya Komatsu, Yusuke Fujita, Yusuke Kida

Personality-aware Training based Speaker Adaptation for End-to-end Speech Recognition

Yue Gu, Zhihao Du, Shiliang Zhang, Qian Chen, Jiqing Han

ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

Edresson Casanova, Christopher Shulby, Alexander Korolev, Arnaldo Candido Junior, Anderson da Silva Soares

Affective attributes of French caregivers' professional speech

Jean-Luc Rouas, Yaru Wu, Takaaki Shochi

Prosody-controllable Gender-ambiguous Speech Synthesis: A Tool for Investigating Implicit Bias in Speech Perception

Eva Szekely, Joakim Gustafson, Ilaria Torre

Developing Speech Processing Pipelines for Police Accountability

Anjalie Field, Prateek Verma, Nay San, Jennifer L. Eberhardt, Dan Jurafsky

Understanding Disrupted Sentences Using Underspecified Abstract Meaning Representation

Angus Addlesee, Marco Damonte

A Multimodal Investigation of Speech, Text, Cognitive and Facial Video Features for Characterizing Depression With and Without Medication

Michael Neumann, Hardik Kothare, Doug Habberstad, Vikram Ramanarayanan

A Multi-Task Learning Framework for Sound Event Detection using High-level Acoustic Characteristics of Sounds

Tanmay Khandelwal, Rohan Kumar Das

MMER: Multimodal Multi-task Learning for Speech Emotion Recognition

Sreyan Ghosh, Utkarsh Tyagi, S Ramaneswaran, Harshvardhan Srivastava, Dinesh Manocha

How to (Virtually) Train Your Speaker Localizer

Prerak Srivastava, Antoine Deleforge, Archontis Politis, Emmanuel Vincent

Background-aware Modeling for Weakly Supervised Sound Event Detection

Yifei Xin, Dongchao Yang, Yuexian Zou

Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains

Jinjin Cai, Sudip Vhaduri, Xiao Luo

Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?

Eklavya Sarkar, Mathew Magimai.-Doss

Hybrid Silent Speech Interface Through Fusion of Electroencephalography and Electromyography

Huiyan Li, Mingyi Wang, Han Gao, Shuo Zhao, Guang Li

Spanish Phone Confusion Analysis for EMG-Based Silent Speech Interfaces

Inge Salomons, Eder del Blanco, Eva Navas, Inma Hernaez

STE-GAN: Speech-to-Electromyography Signal Conversion using Generative Adversarial Networks

Kevin Scheck, Tanja Schultz

Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks

László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Tamás Gábor Csapó

Towards Ultrasound Tongue Image prediction from EEG during speech production

Tamás Gábor Csapó, Frigyes Viktor Arthur, Péter Nagy, Ádám Boncz