Interspeech 2023

1,141 papers

Developmental Articulatory and Acoustic Features for Six to Ten Year Old Children

Vishwas M. Shetty, Steven M. Lulich, Abeer Alwan

Data augmentation for children ASR and child-adult speaker classification using voice conversion methods

Shuyang Zhao, Mittul Singh, Abraham Woubie, Reima Karhila

BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models

Marvin Lavechin, Yaya Sy, Hadrien Titeux, María Andrea Cruz Blandón, Okko Rasanen

Uncertainty Estimation for Connectionist Temporal Classification Based Automatic Speech Recognition

Lars Rumberg, Christopher Gebauer, Hanna Ehlert, Maren Wallbaum, Ulrike Lüdtke

Exploiting Diversity of Automatic Transcripts from Distinct Speech Recognition Techniques for Children’s Speech

Christopher Gebauer, Lars Rumberg, Hanna Ehlert, Ulrike Lüdtke, Joern Ostermann

Using Commercial ASR Solutions to Assess Reading Skills in Children: A Case Report

Timothy Piton, Enno Hermann, Angela Pasqualotto, Marjolaine Cohen, Mathew Magimai.-Doss

Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of /ɹ/ in Child Speech Sound Disorders

Nina R Benway, Yashish M Siriwardena, Jonathan L Preston, Elaine Hitchcock, Tara McAllister

Classifying Rhoticity of /ɹ/ in Speech Sound Disorder using Age-and-Sex Normalized Formants

Nina R Benway, Jonathan L Preston, Asif Salekin, Yi Xiao, Harshit Sharma

Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders

Nina R Benway, Jonathan L Preston

Speech Emotion Recognition using Decomposed Speech via Multi-task Learning

Jia-Hao Hsu, Chung-Hsien Wu, Yu-Hung Wei

Hybrid Dataset for Speech Emotion Recognition in Russian Language

Vladimir Kondratenko, Nikolay Karpov, Artem Sokolov, Nikita Savushkin, Oleg Kutuzov

Dual Memory Fusion for Multimodal Speech Emotion Recognition

Darshana Prisayad, Tharindu Fernando, Sridha Sridharan, Simon Denman, Clinton Fookes

Unsupervised Transfer Components Learning for Cross-Domain Speech Emotion Recognition

Shenjie Jiang, Peng Song, Shaokai Li, Keke Zhao, Wenming Zheng

Speech Emotion Recognition by Estimating Emotional Label Sequences with Phoneme Class Attribute

Ryotaro Nagase, Takahiro Fukumori, Yoichi Yamashita

Improving Joint Speech and Emotion Recognition Using Global Style Tokens

Jehyun Kyung, Ju-Seok Seong, Jeong-Hwan Choi, Ye-Rin Jeoung, Joon-Hyuk Chang

FusedF0: Improving DNN-based F0 Estimation by Fusion of Summary-Correlograms and Raw Waveform Representations of Speech Signals

Eray Eren, Lee Ngee Tan, Abeer Alwan

A Study on the Importance of Formant Transitions for Stop-Consonant Classification in VCV Sequence

Siddarth Chandrasekar, Arvind Ramesh, Tilak Purohit, Prasanta Kumar Ghosh

Improved Contextualized Speech Representations for Tonal Analysis

Jiahong Yuan, Xingyu Cai, Kenneth Church

Matching Acoustic and Perceptual Measures of Phonation Assessment in Disordered Speech - A Case Study

Melanie Jouaiti, Pippa Kirby, Ravi Vaidyanathan

Enhancing Speech Articulation Analysis Using A Geometric Transformation of the X-ray Microbeam Dataset

Ahmed Adel Attia, Mark Tiede, Carol Espy-Wilson

MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion

Woo-Jin Chung, Doyeon Kim, Soo-Whan Chung, Hong-Goo Kang

Implementing Contextual Biasing in GPU Decoder for Online ASR

Iuliia Nigmatulina, Srikanth Madikeri, Esau Villatoro-tello, Petr Motlicek, Juan Zuluaga-Gomez

WhisperX: Time-Accurate Speech Transcription of Long-Form Audio

Max Bain, Jaesung Huh, Tengda Han, Andrew Zisserman

Prefix Search Decoding for RNN Transducers

Kiran Praveen, Advait Vinay Dhopeshwarkar, Abhishek Pandey, Balaji Radhakrishnan

Time-synchronous one-pass Beam Search for Parallel Online and Offline Transducers with Dynamic Block Training

Yui Sudo, Shakeel Muhammad, Yifan Peng, Shinji Watanabe

Automatic Speech Recognition Transformer with Global Contextual Information Decoder

Yukun Qian, Xuyi Zhuang, Mingjiang Wang

Average Token Delay: A Latency Metric for Simultaneous Translation

Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura

STEN-TTS: Improving Zero-shot Cross-Lingual Transfer for Multi-Lingual TTS with Style-Enhanced Normalization Diffusion Framework

Chung Tran, Chi Mai Luong, Sakriani Sakti

Speech inpainting: Context-based speech synthesis guided by video

Juan Felipe Montesinos, Daniel Michelsanti, Gloria Haro, Zheng-Hua Tan, Jesper Jensen

Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations

Wenbin Wang, Yang Song, Sanjay Jha

EdenTTS: A Simple and Efficient Parallel Text-to-speech Architecture with Collaborative Duration-alignment Learning

Youneng Ma, Junyi He, Meimei Wu, Guangyue Hu, Haojun Fei

VISinger2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer

Yongmao Zhang, Heyang Xue, Hanzhao Li, Lei Xie, Tingwei Guo

HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer

Sang-Hoon Lee, Ha-Yeong Choi, Hyung-Seok Oh, Seong-Whan Lee

What’s in a Rise? The Relevance of Intonation for Attention Orienting

Martine Grice

Information Magnitude Based Dynamic Sub-sampling for Speech-to-text

Yuhao Zhang, Chenghao Gao, Kaiqi Kou, Chen Xu, Tong Xiao

Some Voices are Too Common: Building Fair Speech Recognition Systems Using the CommonVoice Dataset

Lucas Maison, Yannick Estève

Everyone has an accent

Nina Markl, Catherine Lai

Improving RNN-Transducers with Acoustic LookAhead

Vinit S. Unni, Ashish Mittal, Preethi Jyothi, Sunita Sarawagi

The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR

Kaousheik Jayakumar, Vrunda N. Sukhadia, A Arunkumar, S Umesh

Blank-regularized CTC for Frame Skipping in Neural Transducer

Yifan Yang, Xiaoyu Yang, Liyong Guo, Zengwei Yao, Wei Kang

Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute

William Chen, Xuankai Chang, Yifan Peng, Zhaoheng Ni, Soumi Maiti

MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations

Calum Heggan, Tim Hospedales, Sam Budgett, Mehrdad Yaghoobi

There is more than one kind of robustness: Fooling Whisper with adversarial examples

Raphael Olivier, Bhiksha Raj

Domain Adaptive Self-supervised Training of Automatic Speech Recognition

Cong-Thanh Do, Rama Doddipatla, Mohan Li, Thomas Hain

Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR

Kaushal Bhogale, Sai Sundaresan, Abhigyan Raman, Tahir Javed, Mitesh M. Khapra

Controlling Multi-Class Human Vocalization Generation via a Simple Segment-based Labeling Scheme

Hieu-Thi Luong, Junichi Yamagishi

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Jungil Kong, Jihoon Park, Beomjeong Kim, Jeongmin Kim, Dohee Kong

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki

FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTs

Won Jang, Dan Lim, Heayoung Park

Controlling formant frequencies with neural text-to-speech for the manipulation of perceived speaker age

Ziya Khan, Lovisa Wihlborg, Cassia Valentini-Botinhao, Oliver Watts

Parameter-Efficient Learning for Text-to-Speech Accent Adaptation

Li-Jen Yang, Chao-Han Huck Yang, Jen-Tzung Chien

Intelligible Lip-to-Speech Synthesis with Speech Units

Jeongsoo Choi, Minsu Kim, Yong Man Ro

Improving WaveRNN with Heuristic Dynamic Blending for Fast and High-Quality GPU Vocoding

Muyang Du, Chuan Liu, Jiaxing Qi, Junjie Lai

ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models

Minki Kang, Wooseok Han, Sung Ju Hwang, Eunho Yang

Hierarchical Timbre-Cadence Speaker Encoder for Zero-shot Speech Synthesis

Joun Yeop Lee, Jae-Sung Bae, Seongkyu Mun, Jihwan Lee, Ji-Hyun Lee

Self-Supervised Solution to the Control Problem of Articulatory Synthesis

Paul K. Krug, Peter Birkholz, Branislav Gerazov, Daniel R. van Niekerk, Anqi Xu

A Low-Resource Pipeline for Text-to-Speech from Found Data With Application to Scottish Gaelic

Dan Wells, Korin Richmond, William Lamb

Automatic Tuning of Loss Trade-offs without Hyper-parameter Search in End-to-End Zero-Shot Speech Synthesis

Seongyeon Park, Bohyung Kim, Tae-Hyun Oh

Real time spectrogram inversion on mobile phone

Oleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang, Xia Zhang

Towards Robust FastSpeech 2 by Modelling Residual Multimodality

Fabian Kögel, Bac Nguyen, Fabien Cardinaux

Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge

Wenhao Guan, Tao Li, Yishuang Li, Hukai Huang, Qingyang Hong

Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech

Hyungchan Yoon, ChangHwan Kim, Eunwoo Song, Hyun-Wook Yoon, Hong-Goo Kang

UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model

Anastasiia Iashchenko, Pavel Andreev, Ivan Shchekotov, Nicholas Babaev, Dmitry Vetrov

Prior-free Guided TTS: An Improved and Efficient Diffusion-based Text-Guided Speech Synthesis

Won-Gook Choi, So-Jeong Kim, Taeho Kim, Joon-Hyuk Chang

ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation

Ambuj Mehrish, Abhinav Ramesh Kashyap, Li Yingting, Navonil Majumder, Soujanya Poria

OverFlow: Putting flows on top of neural transducers for better TTS

Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow, Eva Szekely

Epoch-Based Spectrum Estimation for Speech

Jón Guðnason, Guolin Fang, Mike Brookes

Queer Events, Relationships, and Sports: Does Topic Influence Speakers’ Acoustic Expression of Sexual Orientation?

Sven Kachel, Manuel Pöhlmann, Christine Nussbaum

HumanDiffusion: diffusion model using perceptual gradients

Yota Ueda, Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Hiroshi Saruwatari

L2-Mandarin regional accent variability during Mandarin tone-word training facilitates English listeners’ subsequent tone categorizations

Yanping Li, Michael D. Tyler, Denis Burnham, Catherine T. Best

Emotion Classification with EEG Responses Evoked by Emotional Prosody of Speech

Zechen Zhang, Xihong Wu, Jing Chen

Nasal vowel production and grammatical processing in French-speaking children with cochlear implants and normal-hearing peers.

Sophie Fagniart, Véronique Delvaux, Brigitte Charlier, Bernard Harmegnies, Anne Huberlant

Second language identification of Vietnamese tones by native Mandarin learners

Juqiang Chen, Ailing Qin, Hui Chang, Hua Chen

Head movements in two- and four-person interactive conversational tasks in noisy and moderately reverberant conditions

Alan Archer-Boyd, Rainer Martin

Adaptation to predictive prosodic cues in non-native standard dialect

Sabine Gosselke Berthelsen

Frequency Patterns of Individual Speaker Characteristics at Higher and Lower Spectral Ranges

Zhao Zhang, Ju Zhang, Ziyu Zhu, Yujie Chi, Kiyoshi Honda

Improving End-to-End Modeling For Mandarin-English Code-Switching Using Lightweight Switch-Routing Mixture-of-Experts

Fengyun Tan, Chaofeng Feng, Tao Wei, Shuai Gong, Jinqiang Leng

Leveraging Label Information for Multimodal Emotion Recognition

Peiying Wang, Sunlu Zeng, Junqing Chen, Lu Fan, Meng Chen

Computational modeling of auditory brainstem responses derived from modified speech

Tzu-Han Zoe Cheng, Paul Calamia

Optimal control of speech with context-dependent articulatory targets

Benjamin Elie, Juraj Simko, Alice Turk

Audio, Visual and Audiovisual intelligibility of vowels produced in noise

Maëva Garnier

A Relationship Between Vocal Fold Vibration and Droplet Production

Tsukasa Yoshinaga, Takayuki Arai, Akiyoshi Iida

Assessing Phrase Break of ESL Speech with Pre-trained Language Models and Large Language Models

Zhiyi Wang, Shaoguang Mao, Wenshan Wu, Yan Xia, Yan Deng

Motor Control Similarity Between Speakers Saying “A Souk” Using Inverse Atlas Tongue Modeling

Ursa Maity, Fangxu Xing, Jerry Prince, Maureen Stone, El Fakhri Georges

First Language Effects on Second Language Perception: Evidence from English Low-vowel Nasal Sequences Perceived by L1 Mandarin Chinese Listeners

Sijia Zhang

Enhance Temporal Relations in Audio Captioning with Sound Event Detection

Zeyu Xie, Xuenan Xu, Mengyue Wu, Kai Yu

Few-shot Class-incremental Audio Classification Using Stochastic Classifier

Yanxiong Li, Wenchang Cao, Jialong Li, Wei Xie, Qianhua He

Adapting a ConvNeXt Model to Audio Classification on AudioSet

Thomas Pellegrini, Ismail Khalfaoui-Hassani, Etienne Labbé, Timothée Masquelier

Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning

Jianyuan Sun, Xubo Liu, Xinhao Mei, Volkan Kılıç, Mark D. Plumbley

Acoustic characteristics of depression in older adults' speech: the role of covariates

Carmen Mijnders, Esther Janse, Paul Naarding, Khiet P. Truong

Comparing Hand-Crafted Features to Spectrograms for Autism Severity Estimation

Marina Eni, Ilan Dinstein, Yaniv Zigel

The Androids Corpus: A New Publicly Available Benchmark for Speech Based Depression Detection

Fuxiang Tao, Anna Esposito, Alessandro Vinciarelli

Analysis and automatic prediction of exertion from speech: Contrasting objective and subjective measures collected while running

Andreas Triantafyllopoulos, Alexander Gebhard, Alexander Kathan, Maurice Gerczuk, Shahin Amiriparian

The effect of clinical intervention on the speech of individuals with PTSD: features and recognition performances

Alexander Kathan, Andreas Triantafyllopoulos, Shahin Amiriparian, Sabrina Milkus, Alexander Gebhard

Classification of Vocal Intensity Category from Speech using the Wav2vec2 and Whisper Embeddings

Manila Kodali, Sudarsana Reddy Kadiri, Paavo Alku

Investigating model performance in language identification: beyond simple error statistics

Suzy J. Styles, Victoria Y. H. Chua, Fei Ting Woon, Hexin Liu, Leibny Paola Garcia

Language Identification Networks for Multilingual Everyday Recordings

Kiran Praveen, Balaji Radhakrishnan, Kamini Sabu, Abhishek Pandey, Mahaboob Ali Basha Shaik

Improving wav2vec2-based Spoken Language Identification by Learning Phonological Features

Mostafa Shahin, Zheng Nan, Vidhyasaharan Sethu, Beena Ahmed

Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech

Shashi Kant Gupta, Sushant Hiray, Prashant Kukde

MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization

Victoria Y. H. Chua, Hexin Liu, Leibny Paola Garcia, Fei Ting Woon, Jinyi Wong