{"id":13701693,"url":"https://github.com/yandexdataschool/speech_course","last_synced_at":"2026-01-16T13:21:22.985Z","repository":{"id":43074530,"uuid":"339100588","full_name":"yandexdataschool/speech_course","owner":"yandexdataschool","description":"YSDA course in Speech Processing. ","archived":false,"fork":false,"pushed_at":"2026-01-14T22:13:44.000Z","size":250817,"stargazers_count":304,"open_issues_count":1,"forks_count":91,"subscribers_count":23,"default_branch":"main","last_synced_at":"2026-01-15T03:07:28.318Z","etag":null,"topics":["asr","dsp","tts","vqe"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yandexdataschool.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2021-02-15T14:18:39.000Z","updated_at":"2026-01-14T22:13:50.000Z","dependencies_parsed_at":"2024-02-10T15:27:20.577Z","dependency_job_id":"80e47fda-b39d-4d79-b3cf-e0f68c4b8af3","html_url":"https://github.com/yandexdataschool/speech_course","commit_stats":{"total_commits":130,"total_committers":12,"mean_commits":"10.833333333333334","dds":0.6615384615384615,"last_synced_commit":"58ee4d1a880557ac2095b98a042865e47779cff2"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/yandexdataschool/speech_course","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yandexdataschool%2Fspeech_course","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yandexdataschool%2Fspeech_course/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yandexdataschool%2Fspeech_course/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yandexdataschool%2Fspeech_course/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yandexdataschool","download_url":"https://codeload.github.com/yandexdataschool/speech_course/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yandexdataschool%2Fspeech_course/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28479033,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-16T11:59:17.896Z","status":"ssl_error","status_checked_at":"2026-01-16T11:55:55.838Z","response_time":107,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["asr","dsp","tts","vqe"],"created_at":"2024-08-02T20:01:54.789Z","updated_at":"2026-01-16T13:21:22.980Z","avatar_url":"https://github.com/yandexdataschool.png","language":"Python","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# YSDA Speech Processing Course\n\n- Materials for each week are in ./week* folders\n\n## Course program\n\n- Week 1: Slides | Lecture | Seminar\n    - Lecture: Intro to Digital Signal Processing (DSP)\n    - Seminar: Implement DSP pipeline\n    - Homework (\u003cTBD\u003ept): Implement mel-spectrogram transformations\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\nCourse program for spring 2025\n\u003c/summary\u003e\n\n- Week 1: [Slides](https://docs.google.com/presentation/d/1Cte6w0t8yTJRFirde6GPxKB29VX3SrX1mhAkKYEN-n4/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/E-cGC7pH46UjWQ) | [Seminar](https://disk.yandex.ru/i/j4MsAAliJ5ri_A)\n    - Lecture: Intro to Digital Signal Processing (DSP)\n    - Seminar: Implement DSP pipeline\n    - Homework (5pt): Implement mel-spectrogram transformations\n- Week 2 [Slides](https://docs.google.com/presentation/d/1M3AULJazLVuwJpKsgb5UowcI_XAT6AB8I22ofd1fJY8/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/gyROgNpX5LZNZQ) | [Seminar](https://disk.yandex.ru/i/EwrqSMFQHICVRA):\n    - Lecture: Introduction to speech NN discriminative models. Voice Activity Detection (VAD) and Sound Event Detection (SED) tasks\n    - Seminar: Train VAD models\n    - Homework (15pt): Train SED models\n- Week 3 [Slides](https://docs.google.com/presentation/d/1IppXDfOI2Du5bMfnjxosAgg6Uu0VjXEVRr_8nkUxAus/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/uo6scU9T7R5V9Q) | [Seminar](https://disk.yandex.ru/i/NE6mekhYEQoPGA):\n    - Lecture: Keyword Spotting and Speech Biometrics tasks\n    - Seminar: Train Biometrics model and look at embeddings\n    - Homework (20pt): Train Biometrics model ECAPA-TDNN with contrastive loss\n- Week 4 [Slides](https://docs.google.com/presentation/d/1dU9NasfSDCfgldqJzaaEF2xdamejnGUb4tzu4wbTCPU) | [Lecture](https://disk.yandex.ru/i/_KgUj9Snbl9BsA) | [Seminar](https://disk.yandex.ru/d/e6n-TwqNPyacOw):\n    - Lecture: Speech Recognition I\n    - Seminar: CTC forward-backward, soft alignment\n    - Homework (10pt): CTC/RNN-T decoding, RNN-T forward-backward\n- Week 5 [Slides](https://github.com/yandexdataschool/speech_course/blob/main/week_05_pretraining_asr/lecture.pdf) | [Lecture](https://disk.yandex.ru/d/vownNQ4ZuBARPg) | [Seminar](https://disk.yandex.ru/i/7BtUnWcme2ryag):\n    - Lecture: Speech Recognition II, Pretraining\n    - Homework (5pt): Finetune Wav2Vec2\n- Week 6: [Slides](https://docs.google.com/presentation/d/1BjEEduYCH7z0yKIbL3-t3jaEv90c2r_O6aaMWVXhtRg/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/smC9fVJmXGWOeA) | [Seminar](https://disk.yandex.ru/i/vMn3gnPuH9j3mA)\n    - Lecture: ASR Inference\n    - Seminar: Streaming ASR\n    - Homework (5pt): Seminar continuation\n- Week 7: [Slides](https://docs.google.com/presentation/d/1MAAAc_2vRS2jhxZlqfpx0m7Z3MY9J1jyXgdl7XStFf8/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/d/7w6n6ad8PGxV7w)\n    - Lecture: Text-to-Speech I, intro, preprocessor, metrics\n- Week 8: [Slides](https://docs.google.com/presentation/d/1hR4koanl61qFXNAk2SRp45gYcgxUAc5Xt6_UQJMJYmM/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/THrniTW4cyBnrQ)\n    - Lecture: Text-to-Speech II, Acoustic models and vocoding\n    - Seminar (5pt): Pitch estimation, Monotonic Alignment Search for phoneme duration estimation\n    - Homework (10pt): Train FastPitch model\n- Week 9: [Slides](https://docs.google.com/presentation/d/13pfNuGipGjxlAB754rtQvv_goSFkJR5uTUq4_nCUfWE/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/XCo4vLs3z8UhLw) | [Seminar](https://disk.yandex.ru/i/EVqLrmq1VOyedw)\n    - Lecture: Text-to-Speech III, Codecs\n    - Seminar: Vector Quantizaton, Residual Vector Quantization\n- Week 10: [Slides](https://docs.google.com/presentation/d/1MldH8pnho6BiMHyW3qU8aXspdKarV_sRC1mvvs77FbE/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/uoemA7ga_Rz2mQ)\n    - Lecture: Text-to-Speech IV, Tortoise and other tranformers for TTS\n    - Homework (15pt): write inference for CLM with two transformers\n- Week 11: [Slides](https://docs.google.com/presentation/d/1zfo-vvYHKIFZniDuh-afKif8v8O3272uLSAXm7cFyL8/edit?slide=id.g34b931ff1ac_0_118#slide=id.g34b931ff1ac_0_118) | [Lecture](https://disk.yandex.ru/i/hl_jSEu2fLgWGA)\n    - Lecture: Multimodality, How to build a big GPT with voice capabilities\n- Week 12: [Slides](https://drive.google.com/open?id=1uBAnbciOyoD0VoVdkudPuW3ZeTuAh8wJ\u0026usp=drive_fs) | [Lecture](https://disk.yandex.ru/i/tEFqArlw8vH53g) | [Seminar](https://disk.yandex.ru/i/4ZY96Fsb-si_XQ)\n    - Lecture: noise reduction\n    - Seminar: Streaming STFT and ISTFT\n    - Homework (15pt): Noise reduction model implementation\n- Week 13: [Slides 1](https://drive.google.com/open?id=1tzsZlPC4UPM8wrpuD7LzV3JBJCiW5vmp\u0026usp=drive_fs) | [Slides 2](https://drive.google.com/open?id=1u2WKIt9iPpxFQQUJgxXUeq29YGwz7zMh\u0026usp=drive_fs) | [Lecture+Seminar](https://disk.yandex.ru/i/3gEl2GV22QvEkA)\n    - Lecture: Acoustic Echo Cancelation (AEC) and Beamforming\n    - Homework (5pt): Basic AEC implementation\n\n\u003c/details\u003e\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\nCourse program for spring 2024\n\u003c/summary\u003e\n\n- Week 1: [Slides](https://docs.google.com/presentation/d/1IkVFw8PgWPjn74918rFbuahd7Q38O0f04_bk5_fWPhE/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/eL9PZKCT1O7yhw) | [Seminar](https://disk.yandex.ru/i/ILE1n2aVIWkxEA)\n    - Lecture: Intro to Digital Signal Processing (DSP)\n    - Seminar: Implement DSP pipeline\n- Week 2: [Slides](https://docs.google.com/presentation/d/10cPD8k2oVL2D4wfp4eMBGvSVOShIAfAUgFuqwjedJF4/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/8IwvU8PXAwDKSg) | [Seminar](https://disk.yandex.ru/i/PHaDf7Gzo0LNkA)\n    - Lecture: Introduction to speech NN discriminative models. Voice Activity Detection (VAD) and Sound Event Detection (SED) tasks\n    - Seminar: Train VAD models\n    - Homework: Train SED models\n- Week 3: [Slides](https://docs.google.com/presentation/d/1q5bL4Pdp9MRLJHRuZeabgoHt1KsSg-qGqoEXb_hokW0/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/pGDEBo68YDjenQ) | [Seminar](https://disk.yandex.ru/d/BBpCSG2JLlxf6A)\n    - Lecture: Keyword Spotting and Speech Biometrics tasks\n    - Seminar: Train Biometrics model and look at embeddings\n    - Homework: Train Biometrics model to better quality\n- Week 4: [Slides](https://docs.google.com/presentation/d/1WLjwnJHwjfWfrl31Q3CwwkSEtM5z47LCZ5lXAFk6_Gw/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/QHO1SnqQSkRY6A) | [Seminar](https://disk.yandex.ru/d/87Lrfi1VoH-F8w)\n    - Lecture: Speech Recognition I\n    - Seminar: Metrics and augmentations for speech recognition\n    - Homework: Implement CTC algorithm\n- Week 5: [Slides](https://docs.google.com/presentation/d/1JI8NEjZLNQhbUuO5py3OlYIqMgTPI4LSR-CU3-Rnp9g/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/d/uT9o9bKt60w79g)\n    - Lecture: Speech Recognition II, Pretraining\n    - Homework: Finetune Wav2Vec2\n- Week 6: [Slides](https://docs.google.com/presentation/d/1MAAAc_2vRS2jhxZlqfpx0m7Z3MY9J1jyXgdl7XStFf8/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/X6Se5K14FF91Ow)\n    - Lecture: Text-to-Speech I, intro, preprocessor, metrics\n- Week 7: [Slides](https://docs.google.com/presentation/d/1CO1_5xzZb7mYLfQfdhqN0350dNCkgLt6hHB7smUjdGA/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/YW_TVQMGKbuYag)\n    - Lecture: Text-to-Speech II, Acoustic models\n    - Seminar: Pitch estimation, Monotonic Alignment Search for phoneme duration estimation\n    - Homework: Train FastPitch model\n- Week 8: [Slides, p1](https://docs.google.com/presentation/d/1QU5sUe8_uGEiFs-IFua7EU5_imsZK2TRuKJ_6IY4O9k/edit?usp=sharing) | [Lecture, p1](https://disk.yandex.ru/d/R4p0hupEJrF02g) | [Slides, p2](https://docs.google.com/presentation/d/143qUGId_yvMKx3IDOcErF5M1V6NXHmHp30GuRryhHxs/edit?usp=sharing) | [Lecture, p2](https://disk.yandex.ru/d/abw48YXapfwvfw) | [Seminar](https://disk.yandex.ru/i/XSr1jKD_ah4hkg)\n    - Lecture, p1: Text-to-Speech III, Vocoding\n    - Lecture, p2: Vector Quantization, Codecs\n    - Seminar: Vector Quantizaton, Residual Vector Quantization\n- Week 9: [Slides](https://docs.google.com/presentation/d/1ARlJHMr_c0R2g5Od-66ZTTuZGRxdTCjAzX2LQ9XPFdQ/edit#slide=id.g1f4de8b9e93_0_1414) | [Lecture, p1](https://disk.yandex.ru/i/80GAO85GUjRzKA) | [Lecture, p2](https://disk.yandex.ru/i/icrNEsu17jL7hA)\n    - Lecture: Tranformers for TTS\n    - Homework: write inference for pre-trained transformer\n- Week 10: [Slides](https://docs.google.com/presentation/d/1qq67ydUQpe40Xv5B-lEUWdhB2UMt0rjFuL1--EcqEzU/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/d/olPQZPtFyaTOCw) | [Seminar](https://disk.yandex.ru/i/Dg19n05qIiHT8g)\n    - Lecture: noise reduction\n    - Seminar: Streaming STFT and ISTFT\n    - Homework: Noise reduction model implementation\n- Week 11: [Slides](https://docs.google.com/presentation/d/1JsPBlITpc-a_I_1foWM1tWyO6B3y6OC_AIfmM6CLMr4/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/vGOufpHs8x5mZQ)\n    - Lecture: Acoustic Echo Cancelation (AEC) and Beamforming\n- Week 12: [Slides](https://docs.google.com/presentation/d/1KfiPechci9fmcgi8K9I1_MybAdBo_MwrcK1AYqT4vLI/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/JpgbsaLbpN22Qw) | [Seminar](https://disk.yandex.ru/i/1erd90ueHJjjzw)\n    - Lecture: ASR Inference\n    - Seminar: Streaming ASR\n- Week 13: [Slides](https://docs.google.com/presentation/d/1iwGzbmdJDulfjEvGhw1_oGle8IAjFlalUr_lHWFsVM8/edit?usp=sharing) | [Lecture](https://disk.yandex.ru/i/pXO7D-7JJCjlhQ)\n    - Lecture: Flow based TTS + Voice Conversion\n\n\u003c/details\u003e\n\n## Contributors \u0026 course staff\n\nCurrent:\n- Pavel Mazaev - VAD, SED\n- Alex Rak - spotter, biometry\n- Daniil Volgin - ASR\n- Dzmitry Soupel - ASR\n- Stepan Kargaltsev - ASR\n- Roma Kail - TTS\n- Vladimir Platonov - TTS\n- Vladimir Gogoryan - TTS\n- Ravil Khisamov - VQE\n- Anton Porfirev - AEC\n\nPrevious iteration:\n- Evgeniia Elistratova - TTS lectures, seminars and homeworks\n- Andrey Malinin - Course admin, lectures, seminars, homeworks\n- Vladimir Kirichenko - lectures, seminars, homeworks\n- Segey Dukanov - lecures, seminars, homeworks\n- Evgenii Shabalin - lecture and homework on conversion\n- Mikhail Andreev - ASR\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyandexdataschool%2Fspeech_course","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyandexdataschool%2Fspeech_course","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyandexdataschool%2Fspeech_course/lists"}