Interspeech 2022

1,123 papers

Robust Pitch Estimation Using Multi-Branch CNN-LSTM and 1-Norm LP Residual

Mudit D. Batra, JAYESH, C.S. Ramalingam

Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck

Youngsik Eom, Yeonghyeon Lee, Ji Sub Um, Hoi Rin Kim

Formant Estimation and Tracking using Probabilistic Heat-Maps

Yosi Shrem, Felix Kreuk, Joseph Keshet

Overlapped Frequency-Distributed Network: Frequency-Aware Voice Spoofing Countermeasure

Sunmook Choi, Il-Youp Kwak, Seungsang Oh

Pranay Manocha, Zeyu Jin, Adam Finkelstein

Gram Vaani ASR Challenge on spontaneous telephone speech recordings in regional variations of Hindi

Anish Bhanushali, Grant Bridgman, Deekshitha G, Prasanta Ghosh, Pratik Kumar

Low Resource Comparison of Attention-based and Hybrid ASR Exploiting wav2vec 2.0

Aku Rouhe, Anja Virkkunen, Juho Leinonen, Mikko Kurimo

When Is TTS Augmentation Through a Pivot Language Useful?

Nathaniel Romney Robinson, Perez Ogayo, Swetha R. Gangu, David R. Mortensen, Shinji Watanabe

Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation

Dan Berrebbi, Jiatong Shi, Brian Yan, Osbel López-Francisco, Jonathan Amith

Semi-supervised Acoustic and Language Modeling for Hindi ASR

Tarun Sai Bandarupalli, Shakti Rath, Nirmesh Shah, Onoe Naoyuki, Sriram Ganapathy

ScoutWav: Two-Step Fine-Tuning on Self-Supervised Automatic Speech Recognition for Low-Resource Environments

Kavan Fatehi, Mercedes Torres Torres, Ayse Kucukyilmaz

Data Augmentation for Low-Resource Quechua ASR Improvement

Rodolfo Zevallos, Núria Bel, Guillermo Cámbara, Mireia Farrús, Jordi Luque

Voice Conversion Can Improve ASR in Very Low-Resource Settings

Matthew Baas, Herman Kamper

The 1st Clarity Prediction Challenge: A machine learning challenge for hearing aid intelligibility prediction

Jon Barker, Michael Akeroyd, Trevor J. Cox, John F. Culling, Jennifer Firth

Predicting Speech Intelligibility using the Spike Acativity Mutual Information Index

Franklin Alvarez Cardinale, Waldo Nogueira

Speech Intelligibility Prediction for Hearing-Impaired Listeners with the LEAP Model

Jana Roßbach, Rainer Huber, Saskia Röttges, Christopher F. Hauth, Thomas Biberger

Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction

Zehai Tu, Ning Ma, Jon Barker

Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners

Zehai Tu, Ning Ma, Jon Barker

Non-intrusive Speech Intelligibility Metric Prediction for Hearing Impaired Individuals

George Close, Samuel Hollands, Stefan Goetze, Thomas Hain

Two-Pass Low Latency End-to-End Spoken Language Understanding

Siddhant Arora, Siddharth Dalmia, Xuankai Chang, Brian Yan, Alan W Black

Intent classification using pre-trained language agnostic embeddings for low resource languages

Hemant Yadav, Akshat Gupta, Sai Krishna Rallabandi, Alan W Black, Rajiv Ratn Shah

Deliberation Model for On-Device Spoken Language Understanding

Duc Le, Akshat Shrivastava, Paden D. Tomasello, Suyoun Kim, Aleksandr Livshits

Learning Under Label Noise for Robust Spoken Language Understanding systems

Anoop Kumar, Pankaj Kumar Sharma, Aravind Illa, Sriram Venkatapathy, Subhrangshu Nandi

Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding

Ya-Hsin Chang, Yun-Nung Chen

ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks

Valentin Pelloin, Franck Dary, Nicolas Hervé, Benoit Favre, Nathalie Camelin

Pharyngealization in Amazigh: Acoustic and articulatory marking over time

Philipp Buech, Rachid Ridouane, Anne Hermes

The mapping between syntactic and prosodic phrasing in English and Mandarin

Jianjing Kuang, May Pik Yu Chan, Nari Rhee, Mark Liberman, Hongwei Ding

When Phonetics Meets Morphology: Intervocalic Voicing Within and Across Words in Romance Languages

Mathilde Hutin, Martine Adda-Decker, Lori Lamel, Ioana Vasilescu

Complex sounds and cross-language influence: The case of ejectives in Omani Mehri

Rachid Ridouane, Philipp Buech

VOT and F0 perturbations for the realization of voicing contrast in Tohoku Japanese

Hiroto Noguchi, Sanae Matsui, Naoya Watabe, Chuyu Huang, Ayako Hashimoto

An overview of discourse clicks in Central Swedish

Margaret Zellers

Joint Encoder-Decoder Self-Supervised Pre-training for ASR

A Arunkumar, Srinivasan Umesh

Improved Consistency Training for Semi-Supervised Sequence-to-Sequence ASR via Speech Chain Reconstruction and Self-Transcribing

Heli Qi, Sashi Novitasari, Sakriani Sakti, Satoshi Nakamura

Non-Parallel Voice Conversion for ASR Augmentation

Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Jesse Emond

Speaker adaptation for Wav2vec2 based dysarthric ASR

Murali Karthick Baskar, Tim Herzig, Diana Nguyen, Mireia Diez, Tim Polzehl

CTRL: Continual Representation Learning to Transfer Information of Pre-trained for WAV2VEC 2.0

Jae-Hong Lee, Chae-Won Lee, Jin-Seong Choi, Joon-Hyuk Chang, Woo Kyeong Seong

Unsupervised Data Selection via Discrete Speech Representation for ASR

Zhiyun Lu, Yongqiang Wang, Yu Zhang, Wei Han, Zhehuai Chen

Combining conversational speech with read speech to improve prosody in Text-to-Speech synthesis

Johannah O'Mahony, Catherine Lai, Simon King

BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model

Brooke Stephenson, Laurent Besacier, Laurent Girin, Thomas Hueber

Emphasis Control for Parallel Neural TTS

Shreyas Seshadri, Tuomo Raitio, Dan Castellani, Jiangchuan Li

Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History

Yuto Nishimura, Yuki Saito, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari

Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody

Peter Makarov, Syed Ammar Abbas, Mateusz Łajszczak, Arnaud Joly, Sri Karlapati

CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer

Sri Karlapati, Penny Karanasou, Mateusz Łajszczak, Syed Ammar Abbas, Alexis Moinet

ASR Error Detection via Audio-Transcript entailment

Nimshi Venkat Meripo, Sandeep Konam

Multimodal Depression Severity Score Prediction Using Articulatory Coordination Features and Hierarchical Attention Based Text Embeddings

Nadee Seneviratne, Carol Espy-Wilson

Deep Learning Approaches for Detecting Alzheimer’s Dementia from Conversational Speech of ILSE Study

Ayimnisagul Ablimit, Karen Scholz, Tanja Schultz

Toward Corpus Size Requirements for Training and Evaluating Depression Risk Models Using Spoken Language

Tomasz Rutowski, Amir Harati, Elizabeth Shriberg, Yang Lu, Piotr Chlebek

A Step Towards Preserving Speakers’ Identity While Detecting Depression Via Speaker Disentanglement

Vijay Ravi, Jinhan Wang, Jonathan Flint, Abeer Alwan

ECAPA-TDNN Based Depression Detection from Clinical Speech

Dong Wang, Yanhui Ding, Qing Zhao, Peilin Yang, Shuping Tan

Exploring linguistic feature and model combination for speech recognition based automatic AD detection

Yi Wang, Tianzi Wang, Zi Ye, Lingwei Meng, Shoukang Hu

Impairment Representation Learning for Speech Quality Assessment

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

CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment

Yuchen Liu, Li-Chia Yang, Alexander Pawlicki, Marko Stamenovic

MOSRA: Joint Mean Opinion Score and Room Acoustics Speech Quality Assessment

Karl El Hajal, Milos Cernak, Pablo Mainar

ConferencingSpeech 2022 Challenge: Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications

Gaoxiong Yi, Wei Xiao, Yiming Xiao, Babak Naderi, Sebastian Möller

Soft-label Learn for No-Intrusive Speech Quality Assessment

Junyong Hao, Shunzhou Ye, Cheng Lu, Fei Dong, Jingang Liu

Non-intrusive Speech Quality Assessment with a Multi-Task Learning based Subband Adaptive Attention Temporal Convolutional Neural Network

Xiaofeng Shu, Yanjie Chen, Chuxiang Shang, Yan Zhao, Chengshuai Zhao

MOS Prediction Network for Non-intrusive Speech Quality Assessment in Online Conferencing

Wenjing Liu, Chuan Xie

BIT-MI Deep Learning-based Model to Non-intrusive Speech Quality Assessment Challenge in Online Conferencing Applications

Miao Liu, Jing Wang, Liang Xu, Jianqian Zhang, Shicong Li

Weak supervision for Question Type Detection with large language models

Jiřı́ Martı́nek, Christophe Cerisara, Pavel Kral, Ladislav Lenc, Josef Baloun

Multi-class AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

Menglong Xu, Shengqiang Li, Chengdong Liang, Xiao-Lei Zhang

Hierarchical Tagger with Multi-task Learning for Cross-domain Slot Filling

Xiao Wei, Yuke Si, Shiquan Wang, Longbiao Wang, Jianwu Dang

Phonetic Embedding for ASR Robustness in Entity Resolution

Xiaozhou Zhou, Ruying Bao, William M. Campbell

Large-Scale Streaming End-to-End Speech Translation with Neural Transducers

Jian Xue, Peidong Wang, Jinyu Li, Matt Post, Yashesh Gaur

Exploring representation learning for small-footprint keyword spotting

Fan Cui, Liyong Guo, Quandong Wang, peng gao, Yujun Wang

Negative Guided Abstractive Dialogue Summarization

Junpeng Liu, Yanyan Zou, Yuxuan Xi, Shengjie Li, Mian Ma

XTREME-S: Evaluating Cross-lingual Speech Representations

Alexis CONNEAU, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen

ESSumm: Extractive Speech Summarization from Untranscribed Meeting

Jun Wang

UniKW-AT: Unified Keyword Spotting and Audio Tagging

Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang

Low-complex and Highly-performed Binary Residual Neural Network for Small-footprint Keyword Spotting

Xiao Wang, Song Cheng, Jun Li, Shushan Qiao, Yumei Zhou

An Anchor-Free Detector for Continuous Speech Keyword Spotting

Zhiyuan Zhao, Chuanxin Tang, Chengdong Yao, Chong Luo

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi

End-to-End Joint Modeling of Conversation History-Dependent and Independent ASR Systems with Multi-History Training

Ryo Masumura, Yoshihiro Yamazaki, Saki Mizuno, Naoki Makishima, Mana Ihori

Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children’s Speech

Vishwanath Pratap Singh, Hardik Sailor, Supratik Bhattacharya, Abhishek Pandey

Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech

Samik Sadhu, Hynek Hermansky

Speaker-Specific Utterance Ensemble based Transfer Attack on Speaker Identification

Chu-Xiao Zuo, Jia-Yi Leng, Wu-jun Li

Homophone Disambiguation Profits from Durational Information

Barbara Schuppler, Emil Berger, Xenia Kogler, Franz Pernkopf

Minimizing Sequential Confusion Error in Speech Command Recognition

Zhanheng Yang, Hang Lv, Xiong Wang, Ao Zhang, Lei Xie

A Language Agnostic Multilingual Streaming On-Device ASR System

Bo Li, Tara Sainath, Ruoming Pang, Shuo-Yiin Chang, Qiumin Xu

Significance of single frequency filter for the development of children’s KWS system

Biswaranjan Pattanayak, Gayadhar Pradhan

LAE: Language-Aware Encoder for Monolingual and Multilingual ASR

Jinchuan Tian, Jianwei Yu, Chunlei Zhang, Yuexian Zou, Dong Yu

A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition

Jin Li, Rongfeng Su, Xurong Xie, Lan Wang, Nan Yan

Mitigating bias against non-native accents

Yuanyuan Zhang, YIXUAN ZHANG, Bence Halpern, Tanvina Patel, Odette Scharenborg

Improving Recognition of Out-of-vocabulary Words in E2E Code-switching ASR by Fusing Speech Generation Methods

Lingxuan Ye, Gaofeng Cheng, Runyan Yang, Zehui Yang, Sanli Tian

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems

Mingyu Cui, Jiajun Deng, Shoukang Hu, Xurong Xie, Tianzi Wang

FFM: A Frame Filtering Mechanism To Accelerate Inference Speed For Conformer In Speech Recognition

Zongfeng Quan, Nick J.C. Wang, Wei Chu, Tao Wei, Shaojun Wang

On-the-fly ASR Corrections with Audio Exemplars

Golan Pundak, Tsendsuren Munkhdalai, Khe Chai Sim

Acoustic Stress Detection in Isolated English Words for Computer-Assisted Pronunciation Training

Vera Bernhard, Sandra Schwab, Jean-Philippe Goldman

Global RNN Transducer Models For Multi-dialect Speech Recognition

Takashi Fukuda, Samuel Thomas, Masayuki Suzuki, Gakuto Kurata, George Saon

Cross-Lingual Transfer Learning Approach to Phoneme Error Detection via Latent Phonetic Representation

Jovan M. Dalhouse, Katunobu Itou

VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices

Venkatesh Shenoy Kadandale, Juan F. Montesinos, Gloria Haro

An Improved Transformer Transducer Architecture for Hindi-English Code Switched Speech Recognition

Ansen Antony, Sumanth Reddy Kota, Akhilesh Lade, Spoorthy V, Shashidhar G. Koolagudi

Language-specific interactions of vowel discrimination in noise

Mark Gibson, Marcel Schlechtweg, Beatriz Blecua Falgueras, Judit Ayala Alcalde

Air tissue boundary segmentation using regional loss in real-time Magnetic Resonance Imaging video for speech production

Anwesha Roy, Varun Belagali, Prasanta Ghosh

Acquisition of Two Consecutive Neutral Tones in Mandarin-Speaking Preschoolers: Phonological Representation and Phonetic Realization

Sichen Zhang, Aijun Li

Effects of Noise on Speech Perception and Spoken Word Comprehension

Jovan Eranovic, Daniel Pape, Magda Stroińska, Elisabet Service, Marijana Matkovski

Common and differential acoustic representation of interpersonal and tactile iconic perception of Mandarin vowels

Yi Li, Xiaoming Jiang

Investigating the influence of personality on acoustic-prosodic entrainment

Andreas Weise, Rivka Levitan

InQSS: a speech intelligibility and quality assessment model using a multi-task learning network

Yu-Wen Chen, Yu Tsao

Syllable sequence of /a/+/ta/ can be heard as /atta/ in Japanese with visual or tactile cues

Takayuki Arai, Miho Yamada, Megumi Okusawa

Mandarin Lombard Grid: a Lombard-grid-like corpus of Standard Chinese

Yuhong Yang, Xufeng Chen, Qingmu Liu, Weiping Tu, Hongyang Chen