interspeech

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

INTERSPEECH 2023-2024 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023-24 conference. Explore the latest advances in speech and language processing. Code included. Star the repository to support the advancement of speech technology!

Reading list for research topics in Sound AI

The repository provides links to collections of influential and interesting research papers from top AI conferences, with open-source code to promote reproducibility and provide detailed implementation insights beyond the scope of the article. Stay up to date with the latest advances in AI research!

[InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter

Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.

Code and data repository for paper "VoxCeleb enrichment for Age and Gender recognition" submitted at ASRU 2021

a deep accent recognition network

Supplementary information and code for INTERSPEECH 2018 paper: Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions

Code for our ACML and INTERSPEECH papers: "Speaker Diarization as a Fully Online Bandit Learning Problem in MiniVox".

This repository is the implementation of the paper, "Score-balanced Loss for Multi-aspect Pronunciation Assessment" (Interspeech 2023).

PHO-LID: A Unified Model to Incorporate Acoustic-Phonetic and Phonotactic Information for Language Identification

This repo contains the code for "Voice Disorder Analysis: A Transformer-based Approach", accepted at Interspeech 2024

ITALIC: An ITALian Intent Classification Dataset

[Interspeech 2022] Tutorial - Learning from Weak Labels

Interspeech 2019 experiments

Official code for "Activation Steering for Accent Adaptation in Speech Foundation Models" (Interspeech 2026). Parameter-free accent adaptation via mean-shift steering vectors — no weight updates, consistent WER reductions across 8 accents.

Baseline Experiments for ReMASC dataset.

Code for our INTERSPEECH 2024 paper: Comparing ASR Systems in the Context of Speech Disfluencies.

The implementation code for the paper "Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries"