Interspeech 2024

1,065 papers

Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning

Zhenyu Wang, Shuyu Kong, Li Wan, Biqiao Zhang, Yiteng Huang

Automated content assessment and feedback for Finnish L2 learners in a picture description speaking task

Nhan Phan, Anna von Zansen, Maria Kautonen, Ekaterina Voskoboinik, Tamás Grósz

Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment

Heejin Do, WonJun Lee, Gary Geunbae Lee

Phonological-Level Mispronunciation Detection and Diagnosis

Mostafa Shahin, Beena Ahmed

A Framework for Phoneme-Level Pronunciation Assessment Using CTC

Xinwei Cao, Zijian Fan, Torbjørn Svendsen, Giampiero Salvi

MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarios

Yu-Wen Chen, Zhou Yu, Julia Hirschberg

Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis

Xintong Wang, Mingqian Shi, Ye Wang

Text-only Domain Adaptation for CTC-based Speech Recognition through Substitution of Implicit Linguistic Information in the Search Space

Tatsunari Takagi, Yukoh Wakabayashi, Atsunori Ogawa, Norihide Kitaoka

Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm

Weiran Wang, Zelin Wu, Diamantino Caseiro, Tsendsuren Munkhdalai, Khe Chai Sim

Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU

Daniel Galvez, Vladimir Bataev, Hainan Xu, Tim Kaldewey

Beam-search SIEVE for low-memory speech recognition

Martino Ciaperoni, Athanasios Katsamanis, Aristides Gionis, Panagiotis Karras

E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition

Kun Zou, Fengyun Tan, Ziyang Zhuang, Chenfeng Miao, Tao Wei

Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask

Tianzi Wang, Xurong Xie, Zhaoqing Li, Shoukang Hu, Zengrui Jin

Contextual Biasing Speech Recognition in Speech-enhanced Large Language Model

Xun Gong, Anqi Lv, Zhiming Wang, Yanmin Qian

Exploring the limits of decoder-only models trained on public speech recognition corpora

Ankit Gupta, George Saon, Brian Kingsbury

Lightweight Transducer Based on Frame-Level Criterion

Genshun Wan, Mengzhi Wang, Tingzhi Mao, Hang Chen, Zhongfu Ye

Exploring the Capability of Mamba in Speech Applications

Koichi Miyazaki, Yoshiki Masuyama, Masato Murata

MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels

Darshan Prabhu, Yifan Peng, Preethi Jyothi, Shinji Watanabe

Transmitted and Aggregated Self-Attention for Automatic Speech Recognition

Tian-Hao Zhang, Xinyuan Qian, Feng Chen, Xu-Cheng Yin

Rich speech signal: exploring and exploiting end-to-end automatic speech recognizers’ ability to model hesitation phenomena

Vincenzo Norman Vitale, Loredana Schettino, Francesco Cutugno

How Much Context Does My Attention-Based ASR System Need?

Robert Flynn, Anton Ragni

SEQ-former: A context-enhanced and efficient automatic speech recognition framework

Qinglin Meng, Min Liu, Kaixun Huang, Kun Wei, Lei Xie

InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions

Yu Nakagome, Michael Hentschel

Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity

Tianhua Qi, Shiyan Wang, Cheng Lu, Yan Zhao, Yuan Zong

DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion

Ziqian Ning, Shuai Wang, Pengcheng Zhu, Zhichao Wang, Jixun Yao

FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo

Fine-Grained and Interpretable Neural Speech Editing

Max Morrison, Cameron Churchwell, Nathan Pruyne, Bryan Pardo

Neural Codec Language Models for Disentangled and Textless Voice Conversion

Alan Baade, Puyuan Peng, David Harwath

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune, Yuki Saito, Kanami Imamura

SDAEC: Signal Decoupling for Advancing Acoustic Echo Cancellation

Fei Zhao, Jinjiang Liu, Xueliang Zhang

Efficient Joint Bemforming and Acoustic Echo Cancellation Structure for Conference Call Scenarios

Ofer Schwartz, Sharon Gannot

MSA-DPCRN: A Multi-Scale Asymmetric Dual-Path Convolution Recurrent Network with Attentional Feature Fusion for Acoustic Echo Cancellation

Ye Ni, Cong Pang, Chengwei Huang, Cairong Zou

Low Complexity Echo Delay Estimator Based on Binarized Feature Matching

Yi Gao, Xiang Su

Interference Aware Training Target for DNN based joint Acoustic Echo Cancellation and Noise Suppression

Vahid Khanagha, Dimitris Koutsaidis, Kaustubh Kalgaonkar, Sriram Srinivasan

Multi-mic Echo Cancellation Coalesced with Beamforming for Real World Adverse Acoustic Conditions

Premanand Nayak, Kamini Sabu, M. Ali Basha Shaik

SimuSOE: A Simulated Snoring Dataset for Obstructive Sleep Apnea-Hypopnea Syndrome Evaluation during Wakefulness

Jie Lin, Xiuping Yang, Li Xiao, Xinhong Li, Weiyan Yi

Study Selectively: An Adaptive Knowledge Distillation based on a Voting Network for Heart Sound Classification

Xihang Qiu, Lixian Zhu, Zikai Song, Zeyu Chen, Haojie Zhang

Investigating self-supervised speech models' ability to classify animal vocalizations: The case of gibbon's vocal signatures

Jules Cauzinille, Benoit Favre, Ricard Marxer, Dena Clink, Abdul Hamid Ahmad

DB3V: A Dialect Dominated Dataset of Bird Vocalisation for Cross-corpus Bird Species Recognition

Xin Jing, Luyang Zhang, Jiangjian Xie, Alexander Gebhard, Alice Baird

Vision Transformer Segmentation for Visual Bird Sound Denoising

Sahil Kumar, Jialu Li, Youshan Zhang

Sound of Traffic: A Dataset for Acoustic Traffic Identification and Counting

Shabnam Ghaffarzadegan, Luca Bondi, Wei-Chang Lin, Abinaya Kumar, Ho-Hsiang Wu

FakeSound: Deepfake General Audio Detection

Zeyu Xie, Baihan Li, Xuenan Xu, Zheng Liang, Kai Yu

AnoPatch: Towards Better Consistency in Machine Anomalous Sound Detection

Anbai Jiang, Bing Han, Zhiqiang Lv, Yufeng Deng, Wei-Qiang Zhang

Stream-based Active Learning for Anomalous Sound Detection in Machine Condition Monitoring

Tuan Vu Ho, Kota Dohi, Yohei Kawaguchi

Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection

Hyeonuk Nam, Seong-Hu Kim, Deokki Min, Junhyeok Lee, Yong-Hwa Park

MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection

Da Mu, Zhicheng Zhang, Haobo Yue

Improving Audio Classification with Low-Sampled Microphone Input: An Empirical Study Using Model Self-Distillation

Dawei Liang, Alice Zhang, David Harwath, Edison Thomaz

AlignNet: Learning dataset score alignment functions to enable better training of speech quality estimators

Jaden Pieper, Stephen Voran

Reduce, Reuse, Recycle: Is Perturbed Data Better than Other Language Augmentation for Low Resource Self-Supervised Speech Models

Asad Ullah, Alessandro Ragano, Andrew Hines

YOLOPitch: A Time-Frequency Dual-Branch YOLO Model for Pitch Estimation

Xuefei Li, Hao Huang, Ying Hu, Liang He, Jiabao Zhang

RAST: A Reference-Audio Synchronization Tool for Dubbed Content

David Meyer, Eitan Abecassis, Clara Fernandez-Labrador, Christopher Schroers

Audio Fingerprinting with Holographic Reduced Representations

Yusuke Fujita, Tatsuya Komatsu

M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation

Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Masahiro Yasuda

MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning

Hang Zhao, Yifei Xin, Zhesong Yu, Bilei Zhu, Lu Lu

Exploiting Wavelet Scattering Transform for an Unsupervised Speaker Diarization in Deep Neural Network Framework

Arunav Arya, Murtiza Ali, Karan Nathwani

AFL-Net: Integrating Audio, Facial, and Lip Modalities with a Two-step Cross-attention for Robust Speaker Diarization in the Wild

YongKang Yin, Xu Li, Ying Shan, Yuexian Zou

EEND-M2F: Masked-attention mask transformers for speaker diarization

Marc Harkonen, Samuel J. Broughton, Lahiru Samarakoon

On the Success and Limitations of Auxiliary Network Based Word-Level End-to-End Neural Speaker Diarization

Yiling Huang, Weiran Wang, Guanlong Zhao, Hank Liao, Wei Xia

Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization

Xiang Li, Vivek Govindan, Rohit Paturi, Sundararajan Srinivasan

Investigating Confidence Estimation Measures for Speaker Diarization

Anurag Chowdhury, Abhinav Misra, Mark C. Fuhs, Monika Woszczyna

2.5D Vocal Tract Modeling: Bridging Low-Dimensional Efficiency with 3D Accuracy

Debasish Ray Mohapatra, Victor Zappi, Sidney Fels

Towards a better understanding of receptive multilingualism: listening conditions and priming effects

Wei Xue, Ivan Yuen, Bernd Möbius

Characterizing code-switching: Applying Linguistic Principles for Metric Assessment and Development

Jie Chi, Electra Wallington, Peter Bell

The influence of L2 accent strength and different error types on personality trait ratings

Sarah Wesolek, Piotr Gulgowski, Joanna Blaszczak, Marzena Żygis

Towards Responsible Speech Processing

Isabel Trancoso