<h1>I. Introduction</h1><ul><li><span style="color: rgb(59, 65, 81);">To convert between voices.</span></li><li><strong style="color: rgb(33, 37, 41);">Voice Conversion</strong><span style="color: rgb(33, 37, 41);">&nbsp;is a technology that modifies the speech of a source speaker and makes their speech sound like that of another target speaker without changing the linguistic information.</span></li><li><span style="color: rgb(36, 41, 47);">ESPnet is an end-to-end speech processing toolkit covering end-to-end speech recognition, text-to-speech, speech translation, speech enhancement, speaker diarization, spoken language understanding, and so on. ESPnet uses&nbsp;</span><a href="http://pytorch.org/" rel="noopener noreferrer" target="_blank" style="color: var(--color-accent-fg); background-color: rgb(255, 255, 255);">pytorch</a><span style="color: rgb(36, 41, 47);">&nbsp;as a deep learning engine and also follows&nbsp;</span><a href="http://kaldi-asr.org/" rel="noopener noreferrer" target="_blank" style="color: var(--color-accent-fg); background-color: rgb(255, 255, 255);">Kaldi</a><span style="color: rgb(36, 41, 47);">&nbsp;style data processing, feature extraction/format, and recipes to provide a complete setup for various speech processing experiments.</span></li><li><span style="color: rgb(36, 41, 47);">DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on&nbsp;</span><a href="https://arxiv.org/abs/1412.5567" rel="noopener noreferrer" target="_blank" style="color: var(--color-accent-fg); background-color: rgb(255, 255, 255);">Baidu's Deep Speech research paper</a><span style="color: rgb(36, 41, 47);">. Project DeepSpeech uses Google's&nbsp;</span><a href="https://www.tensorflow.org/" rel="noopener noreferrer" target="_blank" style="color: var(--color-accent-fg); background-color: rgb(255, 255, 255);">TensorFlow</a><span style="color: rgb(36, 41, 47);">&nbsp;to make the implementation easier.</span></li></ul><h1>II. Usage</h1><p>Import input is audio used to Voice Conversion in two ways :</p><ul><li>Import audio by uploading the file</li><li>Import an&nbsp;<strong>ipfs_hash</strong>&nbsp;of audio ( ex :&nbsp;<em>QmPcKEpQb2NVGvuuwH5tkHd9D7ShhgbFhtg8oTCirBUR5M</em>&nbsp;)</li></ul><p>Output a&nbsp;JSON file of the resulting audio</p>

Voice Conversion

<h1>I. Introduction</h1><p>	Used to recognize the topics of a text for Vietnamese.</p><h1>II. Usage</h1><p>Input: The data input is any Vietnamese text used to recognize the topic.</p><p>Output: The data output is the subject of the entered text.</p><h1>III. Example</h1><p>Example text: 'Tôi đi học'.</p><p>Result : 'chinh_tri_xa_hoi'.</p>

Text Classification (Vietnamese)

To recognize the topics of a text for Vietnamese

<p><img src="https://storage.googleapis.com/orailabelstudio/None/user_cc72cf3b-7cdf-444d-9205-5561b33ec7c8/848e73f4-42c5-48e2-8135-31c120d32be9"></p><h3><strong>Overview</strong></h3><p>Voice stress analysis (VSA) is collectively a pseudoscientific technology that aims to infer deception from stress measured in the voice. The technology aims to differentiate between stressed and non-stressed outputs in response to stimuli (e.g., questions posed), with high stress seen as an indication of deception. In this work, we propose a deep learning-based psychological stress detection model using speech signals. With increasing demands for communication between humans and intelligent systems, automatic stress detection is becoming an interesting research topic. Stress can be reliably detected by measuring the level of specific hormones (e.g., cortisol), but this is not a convenient method for the detection of stress in human- machine interactions. The proposed algorithm first extracts Mel- filter bank coefficients using pre-processed speech data and then predicts the status of stress output using a binary decision criterion (i.e., stressed or unstressed) using CNN (Convolutional Neural Network) and dense fully connected layer networks.</p><h3><strong>Need to know</strong></h3><p>You need import input file audio (.wav )</p>

Sentiment Classification

Sentiment classification from voice audio with CNN