20.12.03//Transformer Language Models in ASR. Alexander Zdorovets, MTS

preview_player
Показать описание
#LanguageModels #MTS #aijourney #artificialintelligence
  1. AI Journey
  2. aijourney
  3. artificial intelligence
  4. Language Models
  5. MTS
Рекомендации по теме
Conformer: Convolution-augmented Transformer 0:12:47

Conformer: Convolution-augmented Transformer for Speech Recognition #nlp

03: Hybrid Speech 0:06:59

03: Hybrid Speech Recognition (ASR) System

05: RNN-T ASR 0:10:29

05: RNN-T ASR Training (with an example lattice)

Speech Recognition in 0:26:18

Speech Recognition in Python | finetune wav2vec2 model for a custom ASR model

Fall2022-SpeechRecognition&Understanding (Lecture19 - 1:06:51

Fall2022-SpeechRecognition&Understanding (Lecture19 - End-to-End ASR: CTC)

Streaming Punctuation for 0:25:04

Streaming Punctuation for Long Form Dictation with Transformers

Fall2022-SpeechRecognition&Understanding (Lecture20 - 1:00:43

Fall2022-SpeechRecognition&Understanding (Lecture20 - End-to-End ASR: RNN Transducer)

AST: Audio Spectrogram 0:03:19

AST: Audio Spectrogram Transformer - (3 minutes introduction)

Dan Kaldi #10 0:10:21

Dan Kaldi #10 LibriSpeech run.sh explained

Auto Speech Recognition 0:58:10

Auto Speech Recognition Tutorial, Tools Testing: OpenAI Whisper, Nvidia Conformer, SR, Deepgram, Sps

AudioPaLM: A Large 1:11:48

AudioPaLM: A Large Language Model That Can Speak and Listen

Dan Kaldi #12 0:17:52

Dan Kaldi #12 LibriSpeech run.sh stage 20 Part 2. local/chain/run_tdnn.sh, run_tdnn_1d.sh

IAP @ Gridspace 0:57:55

IAP @ Gridspace 7 - Automatic Speech Recognition (ASR)

Concept to Code: 2:23:05

Concept to Code: Semi-Supervised End-To-End Approaches For Speech Recognition

Self-supervised End-to-End ASR 0:20:32

Self-supervised End-to-End ASR for Low Resource L2 Swedish - (Oral presentation)

Transformer: Attention is 0:56:59

Transformer: Attention is All You Need and Listen, Attend and Spell -- from a Speech Perspective

INTERSPEECH2021: Using Large 0:02:47

INTERSPEECH2021: Using Large Self-Supervised Models for Low-Resource Speech Recognition(3 min Intro)

IAP @ Gridspace 0:55:25

IAP @ Gridspace 6 - Large Language Models and InstructGPT

LTI Colloquium: Latest 1:04:28

LTI Colloquium: Latest Advances in End-to-End Speech Recognition

Confidence Estimation for 0:27:45

Confidence Estimation for Attention based Sequence to Sequence Models for Speech Recognition

Scaling Laws for 0:24:07

Scaling Laws for Neural Language Models

Introduction to Robust 0:43:36

Introduction to Robust Speech Challenge

[ICASSP 2020] MOCKINGJAY: 0:15:00

[ICASSP 2020] MOCKINGJAY: UNSUPERVISED SPEECH REPRESENTATION LEARNING (Speaker: Andy T. Liu)

Multilingual Speech Recognition 0:27:09

Multilingual Speech Recognition Methods using Deep Learning and Cosine Similarity