awesome-speech-recognition-speech-synthesis-papers

Why we included this project

This index of research papers covers the speech and audio field, from classic hidden Markov model and finite-state transducer work to the attention-based sequence-to-sequence and diffusion models used today. If you're new to speech technology, the organization helps you follow how modern ASR and TTS systems evolved instead of dropping you into random papers. For practitioners scoping a project, it works as a reading map: papers are grouped by task (recognition, verification, synthesis, voice conversion, language and music modelling) and each entry links straight to its PDF, so you don't have to dig through arXiv and conference archives. Since it's a bibliography rather than runnable code, treat it as a study companion and a starting point for your own literature review, not as something you deploy.