Questions tagged [speech-recognition]
For questions related to speech recognition, also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT), which is a sub-field of computational linguistics that enables the recognition and translation of spoken language into text by computers.
28
questions
0
votes
1
answer
76
views
With the various text-to-speech tools out there, it possible to achieve the transcript accuracy of Whisper, with the timestamp accuracy of Vosk?
I need to transcript some speech files. I've played around with a number of tools and I found that:
OpenAI Whisper transcribes speech with absolute accuracy. It's even more accurate than me.
However ...
- 123
0
votes
0
answers
9
views
Is mobile-phone speech-recognition geographically/dialect weighted?
When I pronounce the English word "sir" as it is pronounced here, which is American English (at least when I visit that page) my mobile phone thinks I'm saying the name "Sarah" ...
- 101
0
votes
0
answers
23
views
SOTA speech-to-text model for commercial use with access to internal states
I am looking for a speech-to-text model that is available for commercial use (such as Whisper and Chirp) of which full access to the model is possible and performs (near) SOTA. I would like to be able ...
0
votes
0
answers
16
views
Small language model vocabulary correction
I plan to train a small language model (less than 4B parameters) that can run on x86 and handle vocabulary correction such as:
...
2
votes
2
answers
179
views
What is a beam?
For example, faster-whisper's transcribe function takes an argument
beam_size: Beam size to use for decoding.
What does "...
- 163
0
votes
2
answers
62
views
How is speech recognition software able to distinguish between different speakers and yet still understand them all?
Some background: I'm an EE major and data science minor, so I have a basic understanding of machine learning - I had a one semester course on it where we covered some of the most commonly used ...
0
votes
0
answers
39
views
Feature extraction from log-mel spectrograms using CNNs
I am currently working on an ASR-related project in which I would like to combine Convolutional Neural Network with GRU Network and CTC loss function.
The idea is to use the CNN to extract ...
- 1
1
vote
0
answers
29
views
What is the number of channels of input audio mel spectrogram?
What is the number of channels of input audio mel spectrogram? For example, in CV we always have 3 input channels on RGB picture. But what about audio?
7
votes
2
answers
450
views
Term for algorithms that are not trained
Before the advent of neural architectures, many AI domains (e.g. speech recognition and computer vision) used algorithms that consisted of a series of hand-crafted transformations for feature ...
- 181
2
votes
2
answers
3k
views
Open-source vocal cloning (speech-to-speech neural style transfer)
I want to program and train a voice cloner, in part to learn about this area of AI, and in part to use as a prototype of audio for testing and getting feedback from early adopters before recording in ...
- 101
1
vote
0
answers
45
views
How to align or synchronize Youtube caption with audio accurately
I need to use the automatic caption from Youtube to precisely isolate excerpts from the video aligned to text and generate the dataset to train a model in French.
So I've already written the script, ...
- 11
0
votes
2
answers
638
views
What is the difference between the "equal error rate" and "detection cost function" metrics?
I was designing a multi-speaker identification model, so I searched for some metrics that one may use. I found two metrics:
EER (equal error rate)
DCF (detection cost function)
What is the ...
- 361
0
votes
0
answers
44
views
Speech diarization for a conversation detector: A good idea or not?
I am trying to write a program in which an ai can detect whether a conversation is occurring or not. The ai does not need to transcribe words or have any meaning about the conversation, simply if one ...
1
vote
0
answers
24
views
Looking for help on initializing continuous HMM model for word level ASR
I have been studying HMM implementation approaches on ASR for the last couple of weeks. This probabilistic model is very new to me. I am currently using a Python package called Pomegranate to ...
- 11
0
votes
0
answers
125
views
Determining observation and state spaces for viterbi algorithm in a simple word recognition system using HMM
The system I'm trying to implement is a microcontroller with a connected microphone which have to recognise single words. the feature extraction is done using MFCC (and is working).
the system have ...
-1
votes
1
answer
81
views
speech comment detection by deep speech mozilla for data set [closed]
I want to create a system so that when a human being says a word or command through a microphone, such as "shut down", the system can execute that command "shut down".
I used the ...
- 1
4
votes
1
answer
795
views
How do AIs like Siri and Alexa respond to their names being called?
AIs like Siri and Alexa respond to their names being called. How does the system recognize the name by ignoring all the other words that have been said before their name? For example, "Hey Siri&...
0
votes
1
answer
45
views
Studying the speech-generation model and have question about the confusing nature of model input and outputs
I am currently studying this model speech generation known as WaveNet model by Google using the linked original paper and this implementation.
I find the model very confusing in the input it takes and ...
- 181
3
votes
1
answer
425
views
Can transformer be better than RNN for online speech recognition?
Does transformer have the potential to replace RNN end-to-end models for speech recognition for online speech recognition? This mainly depends on accuracy/latency and deploy cost, not training cost. ...
- 199
2
votes
0
answers
549
views
How do I train a multiple-speaker model (speech synthesis) based on Tacotron 2 and espnet?
I'm new to Speech Synthesis & Deep Learning. Recently, I got a task as described below:
I have problem in training a multi-speaker model which should be created by Tacotron2. And I was told I can ...
- 21
3
votes
0
answers
137
views
Speaker Identification / Recognition for less size audio files
I am working on speaker identification problem using GMM (Gaussian Mixture Model). I have to just identify one user present in the given audio, so for second class noise or silent audio may use or not ...
- 358
2
votes
1
answer
497
views
How to use AI for language recognition?
Given an audio track, I'm trying to find a way to recognize the audio language. Only within a small set (e.g. English vs Spanish). Is there a simple solution to detect the language in a speech?
- 973
2
votes
1
answer
3k
views
What is the difference between Kaldi and DeepSpeech speech recognition systems in their approach?
I would like to know how do Kaldi and DeepSpeech speech recognition systems differ algorithmically? Which one would be more accurate for continuous speech in time?
- 31
1
vote
1
answer
95
views
Are there any good ways of simultaneously incorporating object detection with speech recognition?
Are there any good ways of simultaneously incorporating object detection with speech recognition? For example, if you want to identify whether an animal is a dog or cat, we can obviously use visual ...
- 113
1
vote
0
answers
200
views
Keyword spotting with custom keywords and why not use speech recognition instead
My question regards performing keyword spotting for custom keywords and justifying the use of keyword spotting models instead of speech recognition.
I have been doing some searching around Keyword ...
- 597
2
votes
0
answers
32
views
Is there a detailed description or implementation of an end-to-end speech recognition system?
I am currently trying to implement an end-to-end speech recognition system from scratch, that is, without using any of the existing frameworks (like TensorFlow, Keras, etc.). I am building my own ...
- 121
4
votes
1
answer
2k
views
How does the CTC loss work?
I am trying to implement CTC loss in TensorFlow, but their documentation is pretty limited. So I am not sure how to approach the problem. I found a good example in Theano.
Are any other resources that ...
- 41
2
votes
3
answers
145
views
Has there been research done regarding processing speech then building a "speaker profile" based off the processed speech?
Has there been research done regarding processing speech then building a "speaker profile" based off the processed speech? Things like matching the voice with a speaker profile and matching speech ...
- 175