Interspeech 2021

999 papers

Detection of Consonant Errors in Disordered Speech Based on Consonant-Vowel Segment Embedding

Si-Ioi Ng, Cymie Wing-Yee Ng, Jingyu Li, Tan Lee

Phonetic Complexity, Speech Accuracy and Intelligibility Assessment of Italian Dysarthric Speech

Barbara Gili Fivela, Vincenzo Sallustio, Silvia Pede, Danilo Patrocinio

Vocalization Recognition of People with Profound Intellectual and Multiple Disabilities (PIMD) Using Machine Learning Algorithms

Waldemar Jęśko

Analyzing Short Term Dynamic Speech Features for Understanding Behavioral Traits of Children with Autism Spectrum Disorder

Young-Kyung Kim, Rimita Lahiri, Md. Nasir, So Hyun Kim, Somer Bishop

Speech Intelligibility of Dysarthric Speech: Human Scores and Acoustic-Phonetic Features

Wei Xue, Roeland van Hout, Fleur Boogmans, Mario Ganzeboom, Catia Cucchiarini

Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition

Matthew Wiesner, Mousmita Sarma, Ashish Arora, Desh Raj, Dongji Gao

Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System

Ekaterina Egorova, hari Krishna Vydana, Lukas Burget, Jan Černocký

Modeling Dialectal Variation for Swiss German Automatic Speech Recognition

Abbas Khosravani, Philip N. Garner, Alexandros Lazaridis

Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept

Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney

Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition

Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

The CSTR System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages

Ondrej Klejch, Electra Wallington, Peter Bell

M3: MultiModal Masking Applied to Sentiment Analysis

Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos

Separation of Emotional and Reconstruction Embeddings on Ladder Network to Improve Speech Emotion Recognition Robustness in Noisy Conditions

Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso

Speaker Attentive Speech Emotion Recognition

Clément Le Moine, Nicolas Obin, Axel Roebel

Comparing CTC and LFMMI for Out-of-Domain Adaptation of wav2vec 2.0 Acoustic Model

Apoorv Vyas, Srikanth Madikeri, Hervé Bourlard

Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models

Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter

Conditional Independence for Pretext Task Selection in Self-Supervised Speech Representation Learning

Salah Zaiem, Titouan Parcollet, Slim Essid

Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition

Timo Lohrenz, Zhengyang Li, Tim Fingscheidt

Knowledge Distillation for Streaming Transformer–Transducer

Atsushi Kojima

Self-Paced Ensemble Learning for Speech and Audio Classification

Nicolae-Cătălin Ristea, Radu Tudor Ionescu

Lightweight Causal Transformer with Local Self-Attention for Real-Time Speech Enhancement

Koen Oostermeijer, Qing Wang, Jun Du

Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss

Xu Zhang, Xinlei Ren, Xiguang Zheng, Lianwu Chen, Chen Zhang

DBNet: A Dual-Branch Network Architecture Processing on Spectrum and Waveform for Single-Channel Speech Enhancement

Kanghao Zhang, Shulin He, Hao Li, Xueliang Zhang

DCCRN+: Channel-Wise Subband DCCRN with SNR Estimation for Speech Enhancement

Shubo Lv, Yanxin Hu, Shimin Zhang, Lei Xie

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

Xiaohuai Le, Hongsheng Chen, Kai Chen, Jing LU

Deep Noise Suppression with Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data

Ziyi Xu, Maximilian Strake, Tim Fingscheidt

A Simultaneous Denoising and Dereverberation Framework with Target Decoupling

Andong Li, Wenzhe Liu, Xiaoxue Luo, Guochen Yu, Chengshi Zheng

INTERSPEECH 2021 Deep Noise Suppression Challenge

Chandan K.A. Reddy, Harishchandra Dubey, Kazuhito Koishida, Arun Nair, Vishak Gopal

Confidence Intervals for ASR-Based TTS Evaluation

Jason Taylor, Korin Richmond

KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset

Saida Mussakhojayeva, Aigerim Janaliyeva, Almas Mirzakhmetov, Yerbolat Khassanov, Huseyin Atakan Varol

Utilizing Self-Supervised Representations for MOS Prediction

Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao, Yist Y. Lin, Hung-yi Lee

Hi-Fi Multi-Speaker English TTS Dataset

Evelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg, Yang Zhang

Perception of Social Speaker Characteristics in Synthetic Speech

Sai Sirisha Rallabandi, Abhinav Bharadwaj, Babak Naderi, Sebastian Möller

EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model

Chenye Cui, Yi Ren, Jinglin Liu, Feiyang Chen, Rongjie Huang

Comparing Speech Enhancement Techniques for Voice Adaptation-Based Speech Synthesis

Nicholas Eng, C.T. Justine Hui, Yusuke Hioka, Catherine I. Watson

AISHELL-3: A Multi-Speaker Mandarin TTS Corpus

Yao Shi, Hui Bu, Xin Xu, Shaoji Zhang, Ming Li

RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis

Rohola Zandie, Mohammad H. Mahoor, Julia Madsen, Eshrat S. Emamian

Detection and Analysis of Attention Errors in Sequence-to-Sequence Text-to-Speech

Cassia Valentini-Botinhao, Simon King

Spectral and Latent Speech Representation Distortion for TTS Evaluation

Thananchai Kongthaworn, Burin Naowarat, Ekapol Chuangsuwanich

SE-Conformer: Time-Domain Speech Enhancement Using Conformer

Eesung Kim, Hyeji Seo

Learning Speech Structure to Improve Time-Frequency Masks

Suliang Bu, Yunxin Zhao, Shaojun Wang, Mei Han

Speech Enhancement with Topology-Enhanced Generative Adversarial Networks (GANs)

Xudong Zhang, Liang Zhao, Feng Gu

Improved Speech Enhancement Using a Complex-Domain GAN with Fused Time-Domain and Time-Frequency Domain Constraints

Feng Dang, Pengyuan Zhang, Hangting Chen

Speech Denoising Without Clean Training Data: A Noise2Noise Approach

Madhav Mahesh Kashyap, Anuj Tambwekar, Krishnamoorthy Manohara, S. Natarajan

DEMUCS-Mobile : On-Device Lightweight Speech Enhancement

Lukas Lee, Youna Ji, Minjae Lee, Min-Seok Choi

Whisper Speech Enhancement Using Joint Variational Autoencoder for Improved Speech Recognition

Vikas Agrawal, Shashi Kumar, Shakti P. Rath

A Maximum Likelihood Approach to SNR-Progressive Learning Using Generalized Gaussian Distribution for LSTM-Based Speech Enhancement

Xiao-Qi Zhang, Jun Du, Li Chai, Chin-Hui Lee

Single-Channel Speech Enhancement Using Learnable Loss Mixup

Oscar Chang, Dung N. Tran, Kazuhito Koishida

Multi-Stage Progressive Speech Enhancement Network

Xinmeng Xu, Yang Wang, Dongxiang Xu, Yiyuan Peng, Cong Zhang

Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement

Sefik Emre Eskimez, Xiaofei Wang, Min Tang, Hemin Yang, Zirun Zhu

Speech Denoising with Auditory Models

Mark R. Saddler, Andrew Francl, Jenelle Feather, Kaizhi Qian, Yang Zhang

Personalized Speech Enhancement Through Self-Supervised Data Augmentation and Purification

Aswin Sivaraman, Sunwoo Kim, Minje Kim

Leveraging the Uniformity Framework to Examine Crosslinguistic Similarity for Long-Lag Stops in Spontaneous Cantonese-English Bilingual Speech

Khia A. Johnson

Articulatory Characteristics of Icelandic Voiced Fricative Lenition: Gradience, Categoricity, and Speaker/Gesture-Specific Effects

Brynhildur Stefansdottir, Francesco Burroni, Sam Tilsen

Prosody of Case Markers in Urdu

Benazir Mumtaz, Massimiliano Canzi, Miriam Butt

Parsing Speech for Grouping and Prominence, and the Typology of Rhythm

Michael Wagner, Alvaro Iturralde Zurita, Sijia Zhang

The LF Model in the Frequency Domain for Glottal Airflow Modelling Without Aliasing Distortion

Christer Gobl

In-Group Advantage in the Perception of Emotions: Evidence from Three Varieties of German

Moritz Jakob, Bettina Braun, Katharina Zahner-Ritter

Taiwan Min Nan (Taiwanese) Checked Tones Sound Change

Ho-hsien Pan, Shao-ren Lyu

The Interaction of Word Complexity and Word Duration in an Agglutinative Language

Mária Gósy, Kálmán Abari

Targeted and Targetless Neutral Tones in Taiwanese Southern Min

Roger Cheng-yen Liu, Feng-fan Hsieh, Yueh-chin Chang

Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts

Trang Tran, Mari Ostendorf

ProsoBeast Prosody Annotation Tool

Branislav Gerazov, Michael Wagner

An Experiment in Paratone Detection in a Prosodically Annotated EAP Spoken Corpus

Adrien Méli, Nicolas Ballier, Achille Falaise, Alice Henderson

On the Feasibility of the Danish Model of Intonational Transcription: Phonetic Evidence from Jutlandic Danish

Anna Bothe Jespersen, Pavel Šturm, Míša Hejná

How f0 and Phrase Position Affect Papuan Malay Word Identification

Constantijn Kaland, Matthew Gordon

Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning

Dongcheng Jiang, Chao Zhang, Philip C. Woodland

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition

Zhong Meng, Yu Wu, Naoyuki Kanda, Liang Lu, Xie Chen

Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation

Ryo Masumura, Daiki Okamura, Naoki Makishima, Mana Ihori, Akihiko Takashima

4-Bit Quantization of LSTM-Based Speech Recognition Models

Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Xiao Sun, Naigang Wang

Leveraging Non-Target Language Resources to Improve ASR Performance in a Target Language

Jayadev Billa

Scaling Laws for Acoustic Models

Jasha Droppo, Oguz Elibol

Emitting Word Timings with HMM-Free End-to-End System in Automatic Speech Recognition

Xianzhao Chen, Hao Ni, Yi He, Kang Wang, Zejun Ma

Multitask Training with Text Data for End-to-End Speech Recognition

Peidong Wang, Tara N. Sainath, Ron J. Weiss

Regularizing Word Segmentation by Creating Misspellings

Hainan Xu, Kartik Audhkhasi, Yinghui Huang, Jesse Emond, Bhuvana Ramabhadran

Self-Adaptive Distillation for Multilingual Speech Recognition: Leveraging Student Independence

Isabel Leal, Neeraj Gaur, Parisa Haghani, Brian Farris, Pedro J. Moreno

Towards Lifelong Learning of End-to-End ASR

Heng-Jui Chang, Hung-yi Lee, Lin-shan Lee

Model-Agnostic Fast Adaptive Multi-Objective Balancing Algorithm for Multilingual Automatic Speech Recognition Model Training

Jiabin Xue, Tieran Zheng, Jiqing Han

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models

Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

Learning a Neural Diff for Speech Models

Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow

Multi-Domain Knowledge Distillation via Uncertainty-Matching for End-to-End ASR Models

Ho-Gyeong Kim, Min-Joong Lee, Hoshik Lee, Tae Gyoon Kang, Jihyun Lee

Speech Based Depression Severity Level Classification Using a Multi-Stage Dilated CNN-LSTM Model

Nadee Seneviratne, Carol Espy-Wilson

Analysis of Contextual Voice Changes in Remote Meetings

Hector A. Cordourier Maruri, Sinem Aslan, Georg Stemmer, Nese Alyuz, Lama Nachman

Visual Speech for Obstructive Sleep Apnea Detection

Catarina Botelho, Alberto Abad, Tanja Schultz, Isabel Trancoso

TDCA-Net: Time-Domain Channel Attention Network for Depression Detection

Cong Cai, Mingyue Niu, Bin Liu, Jianhua Tao, Xuefei Liu

Non-Verbal Vocalisation and Laughter Detection Using Sequence-to-Sequence Models and Multi-Label Training

Scott Condron, Georgia Clarke, Anita Klementiev, Daniela Morse-Kopp, Jack Parry

Emotion Carrier Recognition from Personal Narratives

Aniruddha Tammewar, Alessandra Cervone, Giuseppe Riccardi

Language or Paralanguage, This is the Problem: Comparing Depressed and Non-Depressed Speakers Through the Analysis of Gated Multimodal Units

Nujud Aloshban, Anna Esposito, Alessandro Vinciarelli

Stacked Recurrent Neural Networks for Speech-Based Inference of Attachment Condition in School Age Children

Huda Alsofyani, Alessandro Vinciarelli

Impact of Emotional State on Estimation of Willingness to Buy from Advertising Speech

Mizuki Nagano, Yusuke Ijima, Sadao Hiroya

Robust Laughter Detection in Noisy Environments

Jon Gillick, Wesley Deng, Kimiko Ryokai, David Bamman

Automatic Speech Recognition Systems Errors for Objective Sleepiness Detection Through Voice

Vincent P. Martin, Jean-Luc Rouas, Florian Boyer, Pierre Philip

Differentiable Allophone Graphs for Language-Universal Speech Recognition

Brian Yan, Siddharth Dalmia, David R. Mortensen, Florian Metze, Shinji Watanabe

Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR

Shammur Absar Chowdhury, Amir Hussein, Ahmed Abdelali, Ahmed Ali

Hierarchical Phone Recognition with Compositional Phonetics

Xinjian Li, Juncheng Li, Florian Metze, Alan W. Black

SRI-B End-to-End System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages

Hardik Sailor, Kiran Praveen T, Vikas Agrawal, Abhinav Jain, Abhishek Pandey

Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition

Genta Indra Winata, Guangsen Wang, Caiming Xiong, Steven Hoi

MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages

Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah, Ankita Singh, Srinivasa Raghavan

Dual Script E2E Framework for Multilingual and Code-Switching ASR

Mari Ganesh Kumar, Jom Kuriakose, Anand Thyagachandran, Arun Kumar A, Ashish Seth

Using Large Self-Supervised Models for Low-Resource Speech Recognition

Krishna D. N, Pinyi Wang, Bruno Bozza