Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Subfield
Audio and speech generation
Benchmarks: LibriSpeech test-clean zero-shot TTS, Seed-TTS eval, LJSpeech single-speaker TTS and vocoding, AudioCaps text-to-audio and others. Datasets: LibriSpeech, LibriTTS, LJSpeech, VCTK and others. Baselines: Tacotron 2, VITS, HiFi-GAN, VALL-E and others.