Interspeech 2023

1,110 papers

Top Research Directions

Research directions most represented by Interspeech 2023 papers.

Learning High-Level Acoustic Structures from Unlabeled Audio 34
The Single Speaker Generalization Bottleneck in Speech Synthesis 29
Partitioning Variance with Linear Mixed Effects Models 26
Zero Shot Speaker Generalization for Speech Synthesis 22
Overcoming Data Scarcity in Low-Resource Speech Recognition 21
Layer Specialization in Deep Speech Representations 20
Temporal Alignment of Speech and Text 20
Cross-Task Generalization in Audio and Speech Processing 19
Speech Analysis for Early Detection of Cognitive Decline 19
Fine Tuning Speech Models for Specialized Domains 19
Universal Acoustic Representations for Cross-Lingual Generalization 19
Generalization to Unseen Acoustic Environments 17
Robust Natural Language Understanding for Noisy Speech Transcripts 17
Generalizing Speech Models to Unseen Acoustic Environments 17
Robust Speech Recognition for Intra-Sentential Code-Switching 17

Top Authors

AuthorPapers
Shinji Watanabe17
Yanmin Qian12
EngSiong Chng10
Haizhou Li9
Zhiyong Wu9
Joon-Hyuk Chang8
Helen M. Meng7
Jianwei Yu7
Jing Xiao7
Lei Xie7
Peter Bell7
Qian Chen7
Bin Ma6
Chao-Han Huck Yang6
Dianwen Ng6
Dong Yu6
Kai Yu6
Bei Liu5
Chong Zhang5
Jesus Villalba5

Impactful Papers

Papers from Interspeech 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Nasal vowel production and grammatical processing in French-speaking children with cochlear implants and normal-hearing peers.
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space
NEMA: An Ecologically Valid Tool for Assessing Hearing Devices, Advanced Algorithms, and Communication in Diverse Listening Environments
NeMo Forced Aligner and its application to word alignment for subtitle generation
Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition
Neural Speech Synthesis with Enriched Phrase Boundaries
Nkululeko: Machine Learning Experiments on Speaker Characteristics Without Programming
Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews
Nonbinary American English speakers encode gender in vowel acoustics
Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals
NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning
NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
North Sámi Dialect Identification with Self-supervised Speech Models
N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition
O-1: Self-training with Oracle and 1-best Hypothesis
Obstructive Sleep Apnea Detection using Pre-trained Speech Representations
Obstructive sleep apnea screening with breathing sounds and respiratory effort: a multimodal deep learning approach
On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
On-Device Speaker Anonymization of Acoustic Embeddings for ASR based on Flexible Location Gradient Reversal Layer
One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics
Online Punctuation Restoration using ELECTRA Model for streaming ASR Systems
On Monotonic Aggregation for Open-domain QA
On the Benefits of Self-supervised Learned Speech Representations for Predicting Human Phonetic Misperceptions
On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognition
On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning
On the N-gram Approximation of Pre-trained Language Models
On the Robustness of Arabic Speech Dialect Identification
On the robustness of wav2vec 2.0 based speaker recognition systems
On the Use of High Frequency Information for Voice Pathology Classification
Ontology-aware Learning and Evaluation for Audio Tagging
On Training a Neural Residual Acoustic Echo Suppressor for Improved ASR
Opening or Closing? An Electroglottographic Analysis of Voiceless Coda Consonants in Australian English
Optimal control of speech with context-dependent articulatory targets
Orthography-based Pronunciation Scoring for Better CAPT Feedback
OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning
OverFlow: Putting flows on top of neural transducers for better TTS
Overlap Aware Continuous Speech Separation without Permutation Invariant Training
Parameter-efficient Dysarthric Speech Recognition Using Adapter Fusion and Householder Transformation
Parameter-Efficient Learning for Text-to-Speech Accent Adaptation
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
Parameter Selection for Analyzing Conversations with Autism Spectrum Disorder
Pardon my disfluency: The impact of disfluency effects on the perception of speaker competence and confidence
Parsing dialog turns with prosodic features in English
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
PCNN: A Lightweight Parallel Conformer Neural Network for Efficient Monaural Speech Enhancement
Perception of Incomplete Voicing Neutralization of Obstruents in Tohoku Japanese
Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR Evaluation

« prev Page 15/23 next »