Interspeech 2023
1,110 papers
Top Research Directions
Research directions most represented by Interspeech 2023 papers.
Top Authors
Impactful Papers
Papers from Interspeech 2023 that shaped research clusters.
Foundational
Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
foundational
Balancing Perceptual Quality and Signal
GRAVO: Learning to Generate Relevant Audio from Visual Features with Noisy Online Videos
foundational
Hierarchical Decoupling of Semantic and
Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affin
foundational
Unsupervised Subpopulation Identificatio
DC CoMix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer
foundational
Language Modeling on Discrete Audio Toke
Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus
foundational
Language Modeling on Discrete Audio Toke
Using Text Injection to Improve Recognition of Personal Identifiers in Speech
foundational
Multimodal Data Mixture Optimization
Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement
foundational
Bypassing Pure Noise Initialization in D
CauSE: Causal Search Engine for Understanding Contact-Center Conversations
foundational
Automated Semantic Labeling with Large L
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
foundational
Exploiting Autoregressive Generation for
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
foundational
Subspace Projection and Parameter Isolat
Influential
Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text
influential
Resolving Lexical Ambiguity from Orthogr
Cross-utterance Conditioned Coherent Speech Editing
influential
Acoustic Boundary Discontinuities in Seg
NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
influential
Signal Restoration in Latent Feature Spa
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speec
influential
Overcoming Statistical Over-Smoothing in
Developmental Articulatory and Acoustic Features for Six to Ten Year Old Children
influential
Smoothing Spline ANOVA for Speech Contou
Exploiting Cross-Domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarth
influential
Recovering Articulatory Movements from S
Classifying Rhoticity of /ɹ/ in Speech Sound Disorder using Age-and-Sex Normalized Formants
influential
Speaker Adaptation for Personalized Spee
Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of /ɹ/ in Child S
influential
Recovering Articulatory Movements from S
DFSNet: A Steerable Neural Beamformer Invariant to Microphone Array Configuration for Real-Time, Low
influential
Array Agnostic Multi Channel Speech Proc
A Personalised Speech Communication Application for Dysarthric Speakers
influential
Speaker Adaptation for Personalized Spee