Learning AI from scratch– category –

Recap and Today's Theme Hello! In the previous episode, we covered keyword spotting (KWS), a technique used to detect specific keywords in real-time, which plays a critical role in voice assistants and smart devices. Today, we will focus...

Recap and Today's Theme Hello! In the previous episode, we discussed emotion recognition from speech, focusing on how audio data can be analyzed to detect the emotions of a speaker. Today, we will explore another important topic: Speaker...

Recap and Today's Theme Hello! In the previous episode, we discussed evaluation metrics for speech recognition systems, such as Word Error Rate (WER), and how these metrics help assess model performance. Today, we will focus on a technol...

Recap and Today's Theme Hello! In the previous episode, we discussed Tacotron 2, a model that generates high-quality speech by converting text into Mel-spectrograms. While Tacotron 2 excels at generating Mel-spectrograms, it still requir...

Recap and Today's Theme Hello! In the previous episode, we explained WaveGlow, a vocoder model that enables high-quality and real-time speech synthesis. By combining WaveGlow with Tacotron 2, we can generate natural-sounding speech effic...

Recap and Today's Theme Hello! In the previous episode, we introduced Text-to-Speech (TTS) technology, which converts text into natural-sounding speech. With advances in deep learning, modern TTS systems, such as Tacotron 2, can generate...

Recap and Today's Theme Hello! In the previous episode, we discussed Wav2Vec, a self-supervised learning model used to extract features from audio data, which significantly improves the accuracy of speech recognition systems. Today, we w...

Recap and Today's Theme Hello! In the previous episode, we discussed Connectionist Temporal Classification (CTC), a method that solves the problem of differing input and output sequence lengths in speech recognition. CTC allows deep lear...

Recap and Today's Theme Hello! In the previous episode, we discussed DeepSpeech, a speech recognition model that utilizes CTC (Connectionist Temporal Classification) and deep learning to convert audio data into text in an end-to-end fash...

Recap and Today's Theme Hello! In the previous episode, we discussed Hidden Markov Models (HMMs), a classical approach to speech recognition. While HMMs decompose speech into phonemes, they face limitations when capturing the complex and...

Recap and Today's Theme Hello! In the previous episode, we explored the basics of speech recognition, understanding how audio is converted into text and how different components like acoustic models and language models work together. Tod...

Recap and Today's Theme Hello! In the previous episode, we discussed noise reduction, learning various techniques to remove noise from audio data to improve its quality. Noise reduction is an essential step in enhancing the overall clari...

Recap and Today's Theme Hello! In the previous episode, we covered audio preprocessing techniques such as normalization, filtering, and adjusting the sampling rate. These steps are essential for improving the quality of audio data and en...

Recap and Today's Theme Hello! In the previous episode, we explored spectrograms, learning how to break down audio signals into frequency components and display them over time. Spectrograms are a crucial tool for visually understanding t...

Recap and Today's Theme Hello! In the previous episode, we discussed Mel-Frequency Cepstral Coefficients (MFCC), a crucial tool for extracting features from audio data used in speech recognition and acoustic analysis. Today, we’ll focus ...