Lists (30)
Acoustic Echo Cancellation
15 repositories
audio effect
41 repositories
Audio Synthesis
2 repositories
BabyCry Det
7 repositories
corpus
10 repositories
database
73 repositories
Hearing Aid
16 repositories
HIFI-DSP
10 repositories
KWS
112 repositories
LLM
868 repositories
machine translation
13 repositories
mic array
3 repositories
Music & Song AGI
13 repositories
Music Source Separation
25 repositories
neural audio codec
200 repositories
NLP
59 repositories
NN algorithm
205 repositories
Pronunciation Assessment
10 repositories
SED
27 repositories
Sound Source Localization
9 repositories
Sound Source Separation
15 repositories
Speaker Diarization
104 repositories
Speaker ID
41 repositories
Speech Enhancement
608 repositories
Speech Recognition
585 repositories
Spoken Language ID
4 repositories
Spoken Language Understanding
9 repositories
Text-to-Speech
758 repositories
TinyML
53 repositories
voice agent
151 repositories
Starred repositories
end-to-end text to audio scene generation model
Parameter-efficient text-to-audio generation for edge and low-memory deployment.
13
Updated May 29, 2026
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Industrial audio online policy distillation (OPD) training stack for ASR and TTS, distilling compact audio models from stronger teacher models.
alphacep / GigaAM
Forked from salute-developers/GigaAMFoundational Model for Speech Recognition Tasks
TugaPhone is a Python library that phonemizes arbitrary Portuguese text across major Lusophone dialects (pt-PT, pt-BR, pt-AO, pt-MZ, pt-TL). It uses a curated phonetic lexicon plus a rule-based fal…
a Python library for phonetic fuzzy searching and segment-to-segment distance computation. It allows you to find words that "sound like" a query by analyzing International Phonetic Alphabet (IPA) f…
A browser-based tool for aligning audio with text transcriptions and IPA (International Phonetic Alphabet) at word, grapheme, and sentence level. Runs entirely client-side, no server, no dependenci…
Official implementation of the Interspeech 2026 paper: UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
Extract a target speaker’s clean, non-overlapped speech from multi-speaker audio and export word-safe LJSpeech-style TTS datasets.
Official implementation of "USAD: Universal Speech and Audio Representation via Distillation"
Zonos2 is a leading open-weight text-to-speech MoE.
Koel Labs innovates open-source speech research, inclusive speech technologies, and real-time pronunciation feedback for language learners! This repo contains the ML training, evaluation, and data …
Codebase for the Interspeech 2026 Paper: MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio
Inference server for MioTTS, a lightweight and fast LLM-based TTS model.
🚀 Fastest Anything-to-Audio Gen for conditioned sound and music creation.
Native full-duplex speech dialogue inference for BayLing-Duplex.