Search Results for "acoustic"
Sort By:
Showing 15 open source projects for "acoustic"
View related business solutions-
Our Free Plans just got better! | Auth0 by OktaYou asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your secuirty. Auth0 now, thank yourself later.
-
Bright Data - All in One Platform for Proxies and Web ScrapingBright Data offers the highest quality proxies with automated session management, IP rotation, and advanced web unlocking technology. Enjoy reliable, fast performance with easy integration, a user-friendly dashboard, and enterprise-grade scaling. Powered by ethically-sourced residential IPs for seamless web scraping.
-
1
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
...-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. -
2
Audiogen Codec
48khz stereo neural audio codec for general audio
AGC (Audiogen Codec) is a convolutional autoencoder based on the DAC architecture, which holds SOTA. We found that training with EMA and adding a perceptual loss term with CLAP features improved performance. These codecs, being low compression, outperform Meta's EnCodec and DAC on general audio as validated from internal blind ELO games. We trained (relatively) very low compression codecs in the pursuit of solving a core issue regarding general music and audio generation, low acoustic quality... -
3
The SpeechBrain Toolkit
A PyTorch-based Speech Toolkit
... in a wide variety of realistic applications. SpeechBrain provides different models for speaker recognition, including X-vector, ECAPA-TDNN, PLDA, and contrastive learning. Spectral masking, spectral mapping, and time-domain enhancement are different methods already available within SpeechBrain. Separation methods such as Conv-TasNet, DualPath RNN, and SepFormer are implemented as well. SpeechBrain provides efficient and GPU-friendly speech augmentation pipelines and acoustic features extraction. -
4
Coqui STT
The deep learning toolkit for speech-to-text
Coqui STT is a fast, open-source, multi-platform, deep-learning toolkit for training and deploying speech-to-text models. Coqui STT is battle-tested in both production and research. Multiple possible transcripts, each with an associated confidence score. Experience the immediacy of script-to-performance. With Coqui text-to-speech, production times go from months to minutes. With Coqui, the post is a pleasure. Effortlessly clone the voices of your talent and have the clone handle the problems... -
ConnectWise Cybersecurity Management for MSPsConnectWise SIEM (formerly Perch) offers threat detection and response backed by an in-house Security Operations Center (SOC). Defend against business email compromise, account takeovers, and see beyond your network traffic. Our team of threat analysts does all the tedium for you, eliminating the noise and sending only identified and verified treats to action on. Built with multi-tenancy, ConnectWise SIEM helps you keep clients safe with the best threat intel on the market.
-
5
AhoTTS - TTS for Basque and Spanish
Text-to-Speech for Basque and Spanish
Text-to-Speech conversor for Basque and Spanish. It includes linguistic processing and built voices for the languages aforementioned. Its acoustic engine is based on hts_engine and it uses a high quality vocoder called AhoCoder. Developed by Aholab Signal Processing Laboratory: https://aholab.ehu.es/aholab/ http://aholab.ehu.es/ahocoder/ -
6
Parakeet
PAddle PARAllel text-to-speech toolKIT
... their reference implementations in PaddlePaddle. Further more, Parakeet abstracts the TTS pipeline and standardizes the procedure of data preprocessing, common module sharing, model configuration, and the process of training and synthesis. The models supported here include Text FrontEnd, end-to-end Acoustic models and Vocoders. -
7
XZVoice
Free and open source text-to-speech software
..., and comprehensively use acoustic parameters and linguistic parameters to establish multiple automatic prediction models based on deep learning. Using massive audio data to train the pronunciation model, the synthetic sound is real, full, cadenced, and expressive, and the MOS score has reached the professional level in the industry. -
8
ASR for Medical Reporting
Automatic speech recognition system for medical reporting in spanish.
This is a functional prototype of automatic speech recognition system for medical reporting in Spanish using CMU Sphinx4 ASR toolkit. This ASR use pre-trained acoustic model and context dependent language model in nuclear medicine diagnostics. -
9
AhoTTS Multilingual, a Multilingual TTS
Text-to-Speech TTS for Basque, Spanish, Catalan, Galician and English
Text-to-Speech conversor for Basque, Spanish, Catalan, Galician and English. It includes linguistic processing and built voices for all the languages aforementioned. Its acoustic engine is based on hts_engine and it uses a high quality vocoder called AhoCoder. Developed by Aholab Signal Processing Laboratory: https://aholab.ehu.es/aholab/ http://aholab.ehu.es/ahocoder/ -
Propelling Payments for Software PlatformsExact Payments delivers easy-to-integrate embedded payment solutions enabling you to rapidly onboard merchants, instantly activate a variety of payment methods and accelerate your revenue — delivering an end-to-end payment processing platform for SaaS businesses.
-
10
FalaBrasil
Resources for speech processing in Brazilian Portuguese
The FalaBrasil Group provides free tools and resources for speech and natural language processing in Brazilian Portuguese, most of them under the BSD license. Tools include mainly scripts to do all sort of things with audio and text, whereas resources include ready-to-used acoustic and languages models, phonetic dictionaries, etc. -
11
midipiano chung is a free open source standalone virtual midi acoustic piano synthesizer /expander with samples based sounds and originals dsps effects, connected to the choozen virtual midi input (up to 3 if any) and midiout(thru) ports of your computer.It is easily extensible by adding or modifying sound files (mp3,wav) in the /sounds/ folder.Works well as output for midi_chung player and midirec_chung recorder or an external usb midi master keyboard. It is written in compiled freebasic...
-
12
kisrecord
A capturing tool for speech data as input for SRS acoustic models
This project follows the target for capturing recordings in combination with the written representation. For the recordings microphones of the kinect are used. The audio files and connected spoken text enable the training of acoustic models for speech recognition. The background is to realize crowd guided open source acoustic models for speech recognition projects like sphinx. -
13
Bavieca (www.bavieca.org)
Bavieca is an open-source speech recognition tookit.
Bavieca (www.bavieca.org) is an open-source speech recognition toolkit intended for speech research and as a platform for rapid development of speech-enabled solutions by non speech experts. It comprises the most common acoustic modeling and adaptation techniques including discriminative training, and efficient dynamic and FSM-based decoders that can operate in batch and live recognition modes. Bavieca is entirely written in C++ and distributed under the Apache 2.0 license. Bavieca... -
14
Anthromorphic Scribe
Provides speech to text gui to sphinx4
It provides an interactive speech to text application that uses sphinx 4. With this you can use pre-recorded audio, record your own voice and convert incompatible audio/video to be compatible with sphinx 4. It currently supports U.S English by using hub4 acoustic and language model. -
15
VoxForge collects user-submitted speech audio files for the creation of Acoustic Models for Free and Open Source Speech Recognition Engines such as HTK, Julius, ISIP and Sphinx.
- Previous
- You're on page 1
- Next