Tubidy
    Understand Microsoft's VALL-E in 3 Minutes (SOTA Zero-shot TTS)

    Understand Microsoft's VALL-E in 3 Minutes (SOTA Zero-shot TTS)

    06:06 |
    Download MP3

    Related Videos

    Deduct OpenAI GPT-4o's Neural Network Architecture 22:56

    Deduct OpenAI GPT-4o's Neural Network Architecture

    Google Researcher's In-Depth Analysis on End-to-End Speech Recognition, Part 1: Overview & Modeling 42:53

    Google Researcher's In-Depth Analysis on End-to-End Speech Recognition, Part 1: Overview & Modeling

    [Olewave's Long Review] Efficient Training of Neural Transducer for Speech Recognition 38:31

    [Olewave's Long Review] Efficient Training of Neural Transducer for Speech Recognition

    Google's Universal Speech Model for 100+ languages beats OpenAI's Whisper Model 56:48

    Google's Universal Speech Model for 100+ languages beats OpenAI's Whisper Model

    Olewave's most detailed illustration of RNN-T: Sequence Transduction with Recurrent Neural Networks 1:40:04

    Olewave's most detailed illustration of RNN-T: Sequence Transduction with Recurrent Neural Networks

    [Olewave's Review] AudioLM: a Language Modeling Approach to Audio Generation 1:11:12

    [Olewave's Review] AudioLM: a Language Modeling Approach to Audio Generation

    [Olewave's Review] CLIP (3/3): Learning Transferable Visual Models From Natural Language Supervision 1:33:00

    [Olewave's Review] CLIP (3/3): Learning Transferable Visual Models From Natural Language Supervision

    [Olewave's Review] CLIP (2/3): Learning Transferable Visual Models From Natural Language Supervision 1:38:05

    [Olewave's Review] CLIP (2/3): Learning Transferable Visual Models From Natural Language Supervision

    [Olewave's Review] OpenAI's Whisper ASR: Robust Speech Recognition via Large-Scale Weak Supervision 44:26

    [Olewave's Review] OpenAI's Whisper ASR: Robust Speech Recognition via Large-Scale Weak Supervision

    [Olewave's Review] CLIP (1/3): Learning Transferable Visual Models From Natural Language Supervision 55:00

    [Olewave's Review] CLIP (1/3): Learning Transferable Visual Models From Natural Language Supervision

    [Olewave's Review] Branchformer: Parallel MLP-Attention Architectures, and E-Branchformer 30:36

    [Olewave's Review] Branchformer: Parallel MLP-Attention Architectures, and E-Branchformer

    [Olewave's Long Review] Xception: Deep Learning with Depthwise Separable Convolutions 51:57

    [Olewave's Long Review] Xception: Deep Learning with Depthwise Separable Convolutions

    [Olewave's Review] Token-level Sequence Labeling for SLU using Compositional E2E Models 55:06

    [Olewave's Review] Token-level Sequence Labeling for SLU using Compositional E2E Models

    A Quick Review of Apple's SOTA Multimodal LLM: MM1 10:11

    A Quick Review of Apple's SOTA Multimodal LLM: MM1

    [Detailed Paper Reading] Zipformer: A faster and better encoder for automatic speech recognition 1:16:59

    [Detailed Paper Reading] Zipformer: A faster and better encoder for automatic speech recognition

    Boris Johnson’s Rise and Fall - an analysis of the mics 9:26

    Boris Johnson’s Rise and Fall - an analysis of the mics

    [Olewave's Short Review] Xception: Deep Learning with Depthwise Separable Convolutions 2:23

    [Olewave's Short Review] Xception: Deep Learning with Depthwise Separable Convolutions

    Why word timestamps generated by OpenAI Whisper are not accurate? How to make them accurate again? 39:12

    Why word timestamps generated by OpenAI Whisper are not accurate? How to make them accurate again?

    Transformer: Attention is All You Need and Listen, Attend and Spell -- from a Speech Perspective 56:59

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

    Tycho:a tookit for building high-ROI in-house speech-related services (ASR/TTS/Translation):Overview 17:07

    Tycho:a tookit for building high-ROI in-house speech-related services (ASR/TTS/Translation):Overview