Interspeech 2024

1,036 papers

Top Research Directions

Research directions most represented by Interspeech 2024 papers.

Learning High-Level Acoustic Structures from Unlabeled Audio 50
Partitioning Variance with Linear Mixed Effects Models 27
Fine Tuning Speech Models for Specialized Domains 22
Overcoming the Modality Gap in Audio Language Models 19
Mitigating the Acoustic Mismatch in Atypical Speech Recognition 19
Overcoming Data Scarcity in Low-Resource Speech Recognition 19
Zero Shot Speaker Generalization for Speech Synthesis 18
Resolving Overlapping Speech in Multi-Speaker Audio 18
The Single Speaker Generalization Bottleneck in Speech Synthesis 18
Temporal Alignment of Speech and Text 17
Speech Analysis for Early Detection of Cognitive Decline 17
Layer Specialization in Deep Speech Representations 16
Visual Anchoring for Robust Speech Enhancement 15
Low-Rank Weight Decomposition for Efficient Model Adaptation 15
Parameter Efficient Speech and Audio Processing 14

Top Authors

AuthorPapers
Shinji Watanabe24
Joon-Hyuk Chang11
Haizhou Li10
Jiatong Shi10
Helen M. Meng9
Jianhua Tao9
Lei Xie9
Hung-yi Lee8
Xixin Wu7
Yanmin Qian7
Chao Zhang6
Xie Chen6
Zhengqi Wen6
EngSiong Chng5
Junlan Feng5
Shrikanth Narayanan5
Yossi Adi5
Yuxun Tang5
Zengrui Jin5
Zhen-Hua Ling5

Impactful Papers

Papers from Interspeech 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Knowledge Distillation from Self-Supervised Representation Learning Model with Discrete Speech Units for Any-to-Any Streaming Voice Conversion
Knowledge-Preserving Pluggable Modules for Multilingual Speech Translation Tasks
LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation
LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems
Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
Large Language Model-based FMRI Encoding of Language Functions for Subjects with Neurocognitive Disorder
Large Language Models for Dysfluency Detection in Stuttered Speech
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks
LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech
Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning
Learning from Back Chunks: Acquiring More Future Knowledge for Streaming ASR Models via Self Distillation
Learning from memory-based models
Learning from Multiple Annotator Biased Labels in Multimodal Conversation
Learning Pronunciation from Other Accents via Pronunciation Knowledge Transfer
Learning Representation of Therapist Empathy in Counseling Conversation Using Siamese Hierarchical Attention Network
Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
Leveraging Adapter for Parameter-Efficient ASR Encoder
Leveraging Graphic and Convolutional Neural Networks for Auditory Attention Detection with EEG
Leveraging Language Model Capabilities for Sound Event Detection
Leveraging large language models for post-transcription correction in contact centers
Leveraging Large Language Models to Refine Automatic Feedback Generation at Articulatory Level in Computer Aided Pronunciation Training
Leveraging Phonemic Transcription and Whisper toward Clinically Significant Indices for Automatic Child Speech Assessment
Leveraging Speech Data Diversity to Document Indigenous Heritage and Culture
Leveraging Universal Speech Representations for Detecting and Assessing the Severity of Mild Cognitive Impairment Across Languages
LibriheavyMix: A 20, 000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
Lifelong Learning MOS Prediction for Synthetic Speech Quality Evaluation
Lightweight Audio Segmentation for Long-form Speech Translation
Lightweight Dynamic Sparse Transformer for Monaural Speech Enhancement
Lightweight Transducer Based on Frame-Level Criterion
Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
Linear-Complexity Self-Supervised Learning for Speech Processing
LingWav2Vec2: Linguistic-augmented wav2vec 2.0 for Vietnamese Mispronunciation Detection
LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition
Listeners' F0 preferences in quiet and stationary noise
LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis
LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
LLM-Driven Multimodal Opinion Expression Identification
Locally Aligned Rectified Flow Model for Speech Enhancement Towards Single-Step Diffusion
LoRA-MER: Low-Rank Adaptation of Pre-Trained Speech Models for Multimodal Emotion Recognition Using Mutual Information
LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR
Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer
Low Complexity Echo Delay Estimator Based on Binarized Feature Matching
Low-dimensional Style Token Control for Hyperarticulated Speech Synthesis
LungAdapter: Efficient Adapting Audio Spectrogram Transformer for Lung Sound Classification

« prev Page 11/21 next »