Interspeech 2023

1,141 papers

When Words Speak Just as Loudly as Actions: Virtual Agent Based Remote Health Assessment Integrating What Patients Say with What They Do

Vikram Ramanarayanan, David Pautler, Lakshmi Arbatti, Abhishek Hosamath, Michael Neumann

NEMA: An Ecologically Valid Tool for Assessing Hearing Devices, Advanced Algorithms, and Communication in Diverse Listening Environments

Nicky Chong-White, Arun Sebastian, Jorge Mejia

My Vowels Matter: Formant Automation Tools for Diverse Child Speech

Hannah Valentine, Joel MacAuslan, Maria Grigos, Marisha Speights

"Select language, modality or put on a mask!" Experiments with Multimodal Emotion Recognition

Paweł Bujnowski, Bartłomiej Kuźma, Bartłomiej Paziewski, Jacek Rutkowski, Joanna Marhula

Promoting Mental Self-Disclosure in a Spoken Dialogue System

Mahdin Rohmatillah, Bobbi Aditya, Li-Jen Yang, Bryan Gautama Ngo, Willianto Sulaiman

Video Multimodal Emotion Recognition System for Real World Applications

Sun-Kyung Lee, Jong-Hwan Kim

A Personalised Speech Communication Application for Dysarthric Speakers

Matthew Gibson, Ievgen Karaulov, Oleksii Zhelo, Filip Jurčíček

Stable Speech Emotion Recognition with Head-k-Pooling Loss

Chaoyue Ding, Jiakui Li, Daoming Zong, Baoxiang Li, Tian-Hao Zhang

Episodic Memory For Domain-Adaptable, Robust Speech Emotion Recognition

James Tavernor, Matthew Perez, Emily Mower Provost

Privacy Risks in Speech Emotion Recognition: A Systematic Study on Gender Inference Attack

Basmah Alsenani, Tanaya Guha, Alessandro Vinciarelli

A Preliminary Study on Augmenting Speech Emotion Recognition using a Diffusion Model

Mohammad Ibrahim Malik, Siddique Latif, Raja Jurdak, Bjorn W. Schuller

The Importance of Calibration: Rethinking Confidence and Performance of Speech Multi-label Emotion Classifiers

Huang-Cheng Chou, Lucas Goncalves, Seong-Gyun Leem, Chi-Chun Lee, Carlos Busso

Personalized Adaptation with Pre-trained Speech Encoders for Continuous Emotion Recognition

Minh Tran, Yufeng Yin, Mohammad Soleymani

Multilingual context-based pronunciation learning for Text-to-Speech

Giulia Comini, Sam Ribeiro, Fan Yang, Heereen Shim, Jaime Lorenzo-Trueba

RAD-MMM: Multilingual Multiaccented Multispeaker Text To Speech

rohan badlani, Rafael Valle, Kevin J. Shih, Joao Felipe Santos, Siddharth Gururani

Generating Multilingual Gender-Ambiguous Text-to-Speech Voices

Konstantinos Markopoulos, Georgia Maniati, Georgios Vamvoukakis, Nikolaos Ellinas, Georgios Vardaxoglou

DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech

Sen Liu, Yiwei Guo, Chenpeng Du, Xie Chen, Kai Yu

Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model

Hoyeon Lee, Hyun-Wook Yoon, Jong-Hwan Kim, Jae-Min Kim

FACTSpeech: Speaking a Foreign Language Pronunciation Using Only Your Native Characters

Hong-Sun Yang, Ji-Hoon Kim, Yoon-Cheol Ju, Il-Hwan Kim, Byeong-Yeol Kim

Automatic Speaker Recognition performance with matched and mismatched female bilingual speech data

Bryony Nuttall, Philip Harrison, Vincent Hughes

Exploring Graph Theory Methods For the Analysis of Pronunciation Variation in Spontaneous Speech

Bernhard C. Geiger, Barbara Schuppler

Automatic speaker recognition with variation across vocal conditions: a controlled experiment with implications for forensics

Vincent Hughes, Jessica Wormald, Paul Foulkes, Philip Harrison, Finnian Kelly

Phonemic competition in end-to-end ASR models

Louis ten Bosch, Martijn Bentum, Lou Boves

On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning

Titouan Parcollet, Shucong Zhang, Rogier van Dalen, Alberto Gil C. P. Ramos, Sourav Bhattacharya

Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition

Jisung Wang, Haram Lee, Myungwoo Oh

Transductive Feature Space Regularization for Few-shot Bioacoustic Event Detection

Yizhou Tan, Haojun Ai, Shengchen Li, Feng Zhang

InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition

Zhi-Hao Lai, Tian-Hao Zhang, Qi Liu, Xinyuan Qian, Li-Fang Wei

Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training

Gege Qi, YueFeng Chen, Xiaofeng Mao, Xiaojun Jia, Ranjie Duan

Re-investigating the Efficient Transfer Learning of Speech Foundation Model using Feature Fusion Methods

Zhouyuan Huo, Khe Chai Sim, Dongseong Hwang, Tsendsuren Munkhdalai, Tara Sainath

Crowdsourced Data Validation for ASR Training

Wannaphong Phatthiyaphaibun, Chompakorn Chaksangchaichot, Thanawin Rakthammanon, Ekapol Chuangsuwanich, Sarana Nutanong

Preference-based training framework for automatic speech quality assessment using deep neural network

Cheng-Hung Hu, Yusuke Yasuda, Tomoki Toda

Probing Speech Quality Information in ASR Systems

Bao Thang Ta, Minh Tu Le, Nhat Minh Le, Van Hai Do

A no-reference speech quality assessment method based on neural network with densely connected convolutional architecture

Wuxuan Gong, Jing Wang, Yitong Liu, Hongwen Yang

The Role of Formant and Excitation Source Features in Perceived Naturalness of Low Resource Tribal Language TTS: An Empirical Study

Ashwini Dasare, Pradyoth Hegde, Supritha Shetty, Deepak K T

DeePMOS: Deep Posterior Mean-Opinion-Score of Speech

Xinyu Liang, Fredrik Cumlin, Christian Schüldt, Saikat Chatterjee

Advances in Language Recognition in Low Resource African Languages: The JHU-MIT Submission for NIST LRE22

Jesus Villalba, Jonas Borgstrom, Maliha Jahan, Saurabh Kataria, Leibny Paola Garcia

Exploring the Impact of Pretrained Models and Web-Scraped Data for the 2022 NIST Language Recognition Evaluation

Tanel Alumäe, Kunnar Kukk, Viet-Bac Le, Claude Barras, Abdel Messaoudi

Description and Analysis of ABC Submission to NIST LRE 2022

Pavel Matějka, Anna Silnova, Josef Slavíček, Ladislav Mošner, Oldřich Plchot

Efficient Spoken Language Recognition via Multilabel Classification

Oriol Nieto, Zeyu Jin, Franck Dernoncourt, Justin Salamon

End to End Spoken Language Diarization with Wav2vec Embeddings

Jagabandhu Mishra, Jayadev N Patil, Amartya Chowdhury, Mahadeva Prasanna

Lightweight and Efficient Spoken Language Identification of Long-form Audio

Winstead Zhu, Md Iftekhar Tanveer, Yang Janet Liu, Seye Ojumu, Rosie Jones

Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation

Yui Sudo, Kazuya Hata, Kazuhiro Nakadai

Memory Network-Based End-To-End Neural ES-KMeans for Improved Word Segmentation

Yu Iwamoto, Takahiro Shinozaki

Memory Augmented Lookup Dictionary Based Language Modeling for Automatic Speech Recognition

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

Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition

Hong Liu, Zhaobiao Lv, Zhijian Ou, Wenbo Zhao, Qing Xiao

Scaling Laws for Discriminative Speech Recognition Rescoring Models

Yile Gu, Prashanth Gurunath Shivakumar, Jari Kolehmainen, Ankur Gandhe, Ariya Rastrow

NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning

Kamer Ali Yuksel, Thiago Castro Ferreira, Golara Javadi, Mohamed Al-badrashiny, Ahmet Gunduz

Transcribing Speech as Spoken and Written Dual Text Using an Autoregressive Model

Mana Ihori, Hiroshi Sato, Tomohiro Tanaka, Ryo Masumura, Saki Mizuno

How to Estimate Model Transferability of Pre-Trained Speech Models?

Zih-Ching Chen, Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen

Language Agnostic Data-Driven Inverse Text Normalization

Szu-Jui Chen, Debjyoti Paul, Yutong Pang, Peng Su, Xuedong Zhang

Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems

Martin Poláček, Petr Cerva, Jindrich Zdansky, Lenka Weingartová

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

Ruan van der Merwe, Herman Kamper

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili

Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper

Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning

Saurabhchand Bhati, Jesus Villalba, Laureano Moro-Velazquez, Thomas Thebaud, Najim Dehak

Distilling knowledge from Gaussian process teacher to neural network student

Jeremy H. M. Wong, Huayun Zhang, Nancy F. Chen

AD-TUNING: An Adaptive CHILD-TUNING Approach to Efficient Hyperparameter Optimization of Child Networks for Speech Processing Tasks in the SUPERB Benchmark

Gaobin Yang, Jun Du, Maokui He, Shutong Niu, Baoxiang Li

Unsupervised Learning of Discrete Latent Representations with Data-Adaptive Dimensionality from Continuous Speech Streams

Shun Takahashi, Sakriani Sakti

CASA-ASR: Context-Aware Speaker-Attributed ASR

Mohan Shi, Zhihao Du, Qian Chen, Fan Yu, Yangze Li

Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling

Ramon Sanabria, Ondrej Klejch, Hao Tang, Sharon Goldwater

Progress and Prospects for Spoken Language Technology: Results from Five Sexennial Surveys

Roger K. Moore, Ricard Marxer

Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization

Puyuan Peng, Brian Yan, Shinji Watanabe, David Harwath

Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model

Puyuan Peng, Shang-Wen Li, Okko Rasanen, Abdelrahman Mohamed, David Harwath

Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer

Lu Huang, Boyu Li, Jun Zhang, Lu Lu, Zejun Ma

Learning When to Trust Which Teacher for Weakly Supervised ASR

Aakriti Agrawal, Milind Rao, Anit Kumar Sahu, Gopinath Chennupati, Andreas Stolcke

Record Deduplication for Entity Distribution Modeling in ASR Transcripts

Tianyu Huang, Chung Hoon Hong, Carl Wivagg, Kanna Shimizu

On the N-gram Approximation of Pre-trained Language Models

Aravind Krishnan, Jesujoba O. Alabi, Dietrich Klakow

Personalization for BERT-based Discriminative Speech Recognition Rescoring

Jari Kolehmainen, Yile Gu, Aditya Gourav, Prashanth Gurunath Shivakumar, Ankur Gandhe

Diacritic Recognition Performance in Arabic ASR

Hanan Aldarmaki, Ahmad Ghannam

Towards Multi-Lingual Audio Question Answering

Swarup Ranjan Behera, Pailla Balakrishna Reddy, Achyut Mani Tripathi, Megavath Bharadwaj Rathod, Tejesh Karavadi

Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech

Shijun Wang, Jón Guðnason, Damian Borth

Differential Privacy enabled Dementia Classification: An Exploration of the Privacy-Accuracy Trade-off in Speech Signal Data

Suhas Bn, Sarah Rajtmajer, Saeed Abdullah

Improving Audio-Text Retrieval via Hierarchical Cross-Modal Interaction and Auxiliary Captions

Yifei Xin, Yuexian Zou

Anomalous Sound Detection Using Self-Attention-Based Frequency Pattern Analysis of Machine Sounds

Hejing Zhang, Jian Guan, Qiaoxi Zhu, Feiyang Xiao, Youde Liu

Joint Prediction of Audio Event and Annoyance Rating in an Urban Soundscape by Hierarchical Graph Representation Learning

Yuanbo Hou, Siyang Song, Cheng Luo, Andrew Mitchell, Qiaoqiao Ren

Background Domain Switch: A Novel Data Augmentation Technique for Robust Sound Event Detection

Wei-Cheng Lin, Luca Bondi, Shabnam Ghaffarzadegan

Personalized Acoustic Scene Classification in Ultra-low Power Embedded Devices Using Privacy-preserving Data Augmentation

Timm Koppelmann, Semih Agcaer, Rainer Martin

Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation

Kangwook Jang, Sungnyun Kim, Se-Young Yun, Hoirin Kim

Topological Data Analysis for Speech Processing

Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov

Interpretable Latent Space Using Space-Filling Curves for Phonetic Analysis in Voice Conversion

Mohammad Hassan Vali, Tom Bäckström

Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes

Wei Xie, Yanxiong Li, Qianhua He, Wenchang Cao, Tuomas Virtanen

Small Footprint Multi-channel Network for Keyword Spotting with Centroid Based Awareness

Dianwen Ng, Yang Xiao, Jia Qi Yip, Zhao Yang, Biao Tian

Fine-tuning Audio Spectrogram Transformer with Task-aware Adapters for Sound Event Detection

Kang Li, Yan Song, Ian McLoughlin, Lin Liu, Jin Li

Resolution Consistency Training on Time-Frequency Domain for Semi-Supervised Sound Event Detection

Won-Gook Choi, Joon-Hyuk Chang

TFECN: Time-Frequency Enhanced ConvNet for Audio Classification

Mengwei Wang, Zhe Yang

Adapting Language-Audio Models as Few-Shot Audio Learners

Jinhua Liang, Xubo Liu, Haohe Liu, Huy Phan, Emmanouil Benetos

Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms

Penghui Wen, Kun Hu, Wenxi Yue, Sen Zhang, Wanlei Zhou

A multimodal prototypical approach for unsupervised sound classification

Saksham Singh Kushwaha, Magdalena Fuentes

Robust Prototype Learning for Anomalous Sound Detection

Xiao-Min Zeng, Yan Song, Ian McLoughlin, Lin Liu, Li-Rong Dai

Selective Biasing with Trie-based Contextual Adapters for Personalised Speech Recognition using Neural Transducers

Philip Harding, Sibo Tong, Simon Wiesler

Probing Self-supervised Speech Models for Phonetic and Phonemic Information: A Case Study in Aspiration

Kinan Martin, Jon Gauthier, Canaan Breiss, Roger Levy

Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search

Yingying Gao, Shilei Zhang, Zihao Cui, Chao Deng, Junlan Feng

Multi-Head State Space Model for Speech Recognition

Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong

Factual Consistency Oriented Speech Recognition

Naoyuki Kanda, Takuya Yoshioka, Yang Liu

Task-Agnostic Structured Pruning of Speech Representation Models

Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang, Suo Hongbin, Yulong Wan

GhostRNN: Reducing State Redundancy in RNN with Cheap Operations

Hang Zhou, Xiaoxu Zheng, Yunhe Wang, Michael Bi Mi, Deyi Xiong

Dual-Mode NAM: Effective Top-K Context Injection for End-to-End ASR

Zelin Wu, Tsendsuren Munkhdalai, Pat Rondon, Golan Pundak, Khe Chai Sim

TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition

Hongfei Xue, Qijie Shao, Peikun Chen, Pengcheng Guo, Lei Xie

LABERT: A Combination of Local Aggregation and Self-Supervised Speech Representation Learning for Detecting Informative Hidden Units in Low-Resource ASR Systems

Kavan Fatehi, Ayse Kucukyilmaz

Iteratively Improving Speech Recognition and Voice Conversion

Mayank Kumar Singh, Naoya Takahashi, Naoyuki Onoe

Transformer-based Speech Recognition Models for Oral History Archives in English, German, and Czech

Jan Lehečka, Jan Švec, Josef V. Psutka, Pavel Ircing