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
Towards Fully Quantized Neural Networks For Speech Enhancement
Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili
Towards Multi-Lingual Audio Question Answering
Towards Multi-task Learning of Speech and Speaker Recognition
Towards Paralinguistic-Only Speech Representations for End-to-End Speech Emotion Recognition
Towards Reference Speech Characterization for Health Applications
Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio
Towards Robust FastSpeech 2 by Modelling Residual Multimodality
Towards robust paralinguistic assessment for real-world mobile health (mHealth) monitoring: an initial study of reverberation effects on speech
Towards Single Integrated Spoofing-aware Speaker Verification Embeddings
Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis
Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features
Towards Two-point Neuron-inspired Energy-efficient Multimodal Open Master Hearing Aid
Towards Ultrasound Tongue Image prediction from EEG during speech production
Tracking Must Go On : Dialogue State Tracking with Verified Self-Training
Transcribing Speech as Spoken and Written Dual Text Using an Autoregressive Model
Transfer Learning for Personality Perception via Speech Emotion Recognition
Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization
Transfer Learning to Aid Dysarthria Severity Classification for Patients with Amyotrophic Lateral Sclerosis
Transformer-based Speech Recognition Models for Oral History Archives in English, German, and Czech
Transforming the Embeddings: A Lightweight Technique for Speech Emotion Recognition Tasks
Transvelar Nasal Coupling Contributing to Speaker Characteristics in Non-nasal Vowels
TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition
TridentSE: Guiding Speech Enhancement with 32 Global Tokens
Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets
Two Stage Contextual Word Filtering for Context Bias in Unified Streaming and Non-streaming Transducer
Two-stage Finetuning of Wav2vec 2.0 for Speech Emotion Recognition with ASR and Gender Pretraining
Two-Stage Voice Anonymization for Enhanced Privacy
Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression
Uncertainty Estimation for Connectionist Temporal Classification Based Automatic Speech Recognition
Understanding Disrupted Sentences Using Underspecified Abstract Meaning Representation
Understanding Spoken Language Development of Children with ASD Using Pre-trained Speech Embeddings
UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model
Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
UniFLG: Unified Facial Landmark Generator from Text or Speech
UniSplice: Universal Cross-Lingual Data Splicing for Low-Resource ASR
UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data
Universal Adversarial Perturbations for Speech Recognition Systems
Universal Automatic Phonetic Transcription into the International Phonetic Alphabet
UnSE: Unsupervised Speech Enhancement Using Optimal Transport
Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition
Unsupervised Adaptation with Quality-Aware Masking to Improve Target-Speaker Voice Activity Detection for Speaker Diarization
Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks
Unsupervised Code-switched Text Generation from Parallel Text
Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space
Unsupervised Learning of Discrete Latent Representations with Data-Adaptive Dimensionality from Continuous Speech Streams
Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance
Unsupervised speech enhancement with deep dynamical generative speech and noise models
Unsupervised Transfer Components Learning for Cross-Domain Speech Emotion Recognition
Use of Speech Impairment Severity for Dysarthric Speech Recognition

« prev Page 21/23 next »