{"adoption": {"forks": 514, "observed_at": "2026-08-28T04:07:45.469355+00:00", "stars": 3130}, "canonical_url": "https://ross.abutalabs.com/products/awesome-speech-recognition-speech-synthesis-papers", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)", "domain": ["speech-processing", "tutorials", "artificial-intelligence"], "enriched": true, "function": ["speech-recognition", "tts", "nlp", "audio-processing", "documentation"], "health_score": 20, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["zzw922cn/awesome-speech-recognition-speech-synthesis-papers"], "name": "zzw922cn/awesome-speech-recognition-speech-synthesis-papers", "platform": ["cross-platform"], "pushed_at": "2023-10-19T03:52:13+00:00", "repo": "zzw922cn/awesome-speech-recognition-speech-synthesis-papers", "stars": 3130, "tags": ["awesome-list", "papers", "asr", "voice-conversion", "speaker-verification", "singing-voice-synthesis", "deep-learning", "audio"], "topics": ["automatic-speech-recognition", "papers", "roadmap", "rnn", "cnn", "dnn", "attention-mechanism", "seq2seq", "acoustic-model", "timit-dataset", "tts", "language-model", "speaker-verification", "speech-recognition", "speech-synthesis", "neural-network", "recognition-synthesis", "diffusion-models", "singing-voice-synthesis", "voice-conversion"], "urls": [], "use_cases": ["find papers on automatic speech recognition", "learn about text-to-speech research history", "get a roadmap for studying speech synthesis", "find voice conversion and speaker verification papers", "discover text-to-audio and music generation papers", "survey deep learning approaches to speech"], "what_it_is": "A curated awesome-list of research papers on speech recognition, speech synthesis, speaker verification, voice conversion, and language modelling, spanning classic HMM work to modern diffusion-based audio generation. It serves as a reading roadmap rather than runnable software.", "when_to_avoid": ["you need runnable speech recognition or TTS code", "you want a maintained library or tool rather than a paper index", "you need tutorials with code examples instead of paper links"], "when_to_choose": ["you need a curated paper list covering ASR and TTS from the 1980s to today", "you are a researcher or student building a reading plan for speech processing", "you want references spanning classic HMM methods to diffusion models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-speech-recognition-speech-synthesis-papers", "repo": "zzw922cn/awesome-speech-recognition-speech-synthesis-papers", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.469355+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:26:17.175112+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d22c2e53af1251896ea7b35dd8335a19be84374cc211ac3edae56d6af9065fd3", "fetched_at": "2026-08-28T04:07:45.469355+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3414, "days_push": 1049, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}