Questions tagged [speech-to-text]
The speech-to-text tag has no usage guidance.
46
questions
0
votes
0
answers
11
views
Decoder model selection for sequence-to-sequence ASR with XLS-R
I am new to building models for Speech ASR. I want to build a model for Speech Transcription in Urdu. I used XLS-R (following the example by Patric von Platen on Huggingface Colab notebook. My ...
0
votes
0
answers
33
views
Proven approaches for labeling recordings for training a speech-to-text model
To train a deep learning model, for converting speech to text, we need labeled data. How should this data be arranged?
I'm interested in building the model from scratch and not using ready-made ...
1
vote
0
answers
22
views
Speech to Text for Unsupported Language
I'm working on a project to plug the good old speech recognition in my app. However, I wish to do it in my country's dialect which is not supported by the major APIs like Azure, AWS, etc.
My country's ...
0
votes
0
answers
14
views
Hidden Markov Model is not accurate with me
I am new to Speech Recognition and want to implement a simple words classifier that predicts the spoken word is one of the 100 words I have in my system. So I have a dataset of audios with every ...
0
votes
0
answers
7
views
input shape in ASR training
Sorry for stupid question but can someone say what is the shape of input batch in ASR training? Because as I understood, if we work with spectrogram we got something like
...
0
votes
0
answers
889
views
OpenAI whisper for realtime transcription
I am using OpenAI whisper for audio to text conversion. I think this is pretty good for offline speech to text, however, the problem is we want to use it in live transcription, as we use google speech ...
0
votes
1
answer
73
views
Are there any pre-trained non english model of deepspeech?
I want to try deepspeech model.
I founded only english pre-trained model
Are there any other pre-trained not english model of ...
0
votes
0
answers
23
views
Labeling tool for ASR to either create audio or transcripts
Is there a labeling tool where I can create audio-transcription-pairs in both directions:
record audio for given text
create transcriptions for given audio?
What I have tried so far:
I went through ...
0
votes
0
answers
45
views
Which decoder method is used with “facebook/wav2vec2-base-960h”?
When using wav2vec2:
facebook/wav2vec2-base-960h
Which decoder method is used when running
processor.decode ?
Naive Decoding or Beam Search or Language Model ?
How can I see it on the ...
0
votes
0
answers
13
views
When using wav2vec2 inference, does the quantitation being used?
According to wav2vec model:
it seems that quantitation only used on training phase (in order to train the transformer layer to quantitative the data to use small number of discrete values).
So my ...
0
votes
1
answer
21
views
Speech to text to microphone
Is it possible to use an artificial intelligence voice as a microphone in real time? I would like something where I could speak and it would be spoken by an AI, such as Cortana's voice, and pass it to ...
0
votes
0
answers
30
views
Procedure or term for analyzing transcribed text and returning bulleted output
I am attempting to analyze transcribed text from an audio file to group bullet points based on known key phrases in the text.
Example: I have verbally stated the following keywords in the text, which ...
0
votes
2
answers
474
views
NameError: name 'librosa' is not defined [closed]
i'm working on Arabic Speech Recognition using Wav2Vec XLSR model.
While fine-tuning the model it gives the error shown in the picture below.
i can't understand what's the problem with librosa it's ...
0
votes
1
answer
41
views
Evaluate Text-to-speech without Human Involved?
I've explored text-to-speech evaluation matrices and they seem to used Mean Opinion Score (MOS) to evaluate a particular model. This matrice required humans to help to judge the model based on a scale ...
3
votes
1
answer
48
views
How to double audio dataset?
I am trying to develop a mispronunciation detection model for English speech. I use TIMIT dataset, this is phoneme labeled audio dataset.
A phoneme is any of the perceptually distinct units of sound. ...
1
vote
0
answers
29
views
How do I initialize a Hidden Markov Model when using MFCC features for speech recognition?
I have a personal dataset of 10000 audio files, each consisting a single spoken sentence. These files each have the transcribed text labels with them that I can use for supervised HMM training.
Now ...
1
vote
1
answer
615
views
How does Wav2Vec 2.0 feed output from Convolutional Feature Encoder as input to the Transformer Context Network
I was reading the Wav2Vec 2.0 paper and trying to understand the model architecture, but I have trouble understanding how audio raw inputs of variable lengths can be fed through the model, especially ...
0
votes
0
answers
32
views
How to build a speech corpus for continuous speech?
I am developing a speech corpus from audiobooks. I was able to collect recordings with their transcriptions but without timing information. Therefore I am looking for recent techniques to ...
2
votes
2
answers
171
views
How to evaluate the quality of speech-to-text data without access to the true labels?
I am dealing with a data set of transcribed call center data, where customers are being recorded when interacting with the agent. This is then automatically transcribed by an external transcription ...
2
votes
0
answers
134
views
How to do phoneme segmentation using dynamic time warping?
Background Information:
Dynamic Time Warping (DTW):
In time series analysis, dynamic time warping (DTW) is one of the
algorithms for measuring similarity between two temporal sequences,
which may ...
2
votes
1
answer
81
views
How is an ASR's output compared to ground truth for validation?
I am curious how it is done as I am interested in doing something similar. I have some manually transcribed data that contains tags for multiple speakers. I want to compare how well the out of the box ...
0
votes
1
answer
40
views
About building database for persian speech to text project [closed]
In connection with the persian speech to text project on github, I am trying to collect the database from the audio and text available on the ganjoor site and Youtube Persian videos with Persian ...
0
votes
1
answer
2k
views
AttributeError: 'Functional' object has no attribute 'uses_learning_phase'
I am trying to predict on my test set and I get the following error
AttributeError: 'Functional' object has no attribute 'uses_learning_phase'
The model is created ...
0
votes
0
answers
390
views
How to change voice features in python without affecting speech/language features?
I am trying to build a CNN model which should be able to identify the language being spoken in an audio file. I have extracted the MFCC matrix (for 13 coefficients) for each audio file and trained it....
1
vote
1
answer
364
views
How to prepare Audio-text data for speech recognition
I have gathered some raw audio from all the conferences, meetings, lectures & casual conversation that I was part of. The machine transcription did not offer good results (from Azure, AWS etc.) I ...
0
votes
1
answer
1k
views
ValueError: Error when checking input: expected the_input to have 3 dimensions, but got array with shape (14174, 1)
hope you're all doing good !
I am working on Automatic Speech Recognition with Python with the LibriSpeech Dataset.
After preprocessing the audios data and applying an "MFCC featurizing" I ...
1
vote
0
answers
30
views
How to make sense of the input and output for a speech-generation model like WaveNet?
I am currently studying this model speech generation known as WaveNet model by Google. https://arxiv.org/pdf/1609.03499.pdf using the linked original paper and this implementation.
I find the model ...
1
vote
2
answers
32
views
Inconsistency on A. Graves' original Connectionist Temporal Classification (CTC) paper?
Here's the link to the paper.
For the forward-backward algorithm, they introduce $\alpha_t(s)$ as a definition in eq. (5).
Then they give a recursive formula for it (eq. (6)), and its initialization. ...
0
votes
1
answer
56
views
Split text into phrases of a person and an operator
I have about 5,000 texts without punctuation marks.
Each text is a conversation between an operator and a person.
For example: "Hello hello how can I help you how can I find out how much money I have ...
1
vote
1
answer
182
views
Conv1D specify output chanels in tensorflow 2.1
Hello I'm trying to implement the "Tacotron Towards end to end" paper and in the
Encoder CBHG - a Conv1D bank of K=16, conv-k-128-ReLU
“conv-k-c-ReLU” - denotes 1-D ...
0
votes
1
answer
38
views
Detection of anomal data in the text
I work with texts where there is a dialogue between two people (a client and a call center employee, the beginning and end of each person’s phrase is not defined). My goal is to classify texts in ...
1
vote
1
answer
61
views
Why gaussian assumption in GMM-HMM ASR?
I am reading a book entitled Speech and Language Processing by Daniel Jurafsky and James.
For Acoustic vector, I would like to know why Gaussian assumption is made?
I searched over the internet and ...
2
votes
2
answers
307
views
Creating pronunciation dictionary for ASR
I am working on ASR(automatic speech recoginition) on Somali data as master thesis and now I am stuck with how to create a phonetics or pronunciation dictionary for it. I searched over net and could ...
2
votes
1
answer
136
views
GMM in speech recoginition using HMM-GMM
I am trying to solve/understand ASR using HMM-GMM.
At the abstract level i do understand what's happening but I did not
understand how GMM fits into it.
My data has 5K hours of speech from single ...
3
votes
1
answer
230
views
ASR on low dataset
I am doing an ASR(automatic speech recognition) as master thesis on low key dataset. Voice and text data is labelled. There are around 4000 phrases and around 5 hours speech.
I don't have background ...
2
votes
2
answers
163
views
where to start in natural language processing for a language
My native language is a regional language and few people speak it. I have some assignements in a machine learning course and i was thinking about doing some natural languge processing on my native ...
0
votes
2
answers
506
views
Training an acoustic model for a speech-to-text engine
What are the steps for training an acoustic model? The format of the data (the audio) includes its length and other characteristics. If anyone could provide a simple example of how to train an ...
0
votes
1
answer
44
views
What to use in setting up a Speech to Text engine in production?
So i have the task to study the feasability of setting up a Speech-To-Text engine in a production environnement, and i've been researching on this topic, so I tried Google's Speech-To-Text API and ...
1
vote
1
answer
228
views
Segment 5-7 min audio into sentence wise audio clips for creating speech recognition dataset
I am trying to create a speech recognition dataset, especially for Indian Accents.
I am taking from colleagues to build this.
Daily I send an article link and ask them to record and upload it to ...
1
vote
1
answer
75
views
Can I create a good Speech Recognition Engine while having millions of recorded conversations?
I have at my disposal millions of wav files containing recorded conversations between employees and clients, i'm doing some research on the possibility of creating a good speech recognition engine. I'...
0
votes
1
answer
47
views
Opensource Speech Recognition Library that is secure and trained on large data [closed]
For all those who are working on developing a chatbot/assistant and care about the privacy of users consuming the speech recognition library, can you suggest an open souce library which is trained on ...
4
votes
1
answer
71
views
Why are observation probabilities modelled as Gaussian distributions in HMM?
HMM is a statistical model with unobserved (i.e. hidden) states used for recognition algorithms (speech, handwriting, gesture, ...). What distinguishes DHMM form CHMM is the transition probability ...
2
votes
0
answers
53
views
Representing output label for character level speec recognition using RNN
I saw this tutorial on generating text using LSTM. In this tutorial the author trained the network by taking 100 previous characters as input and the next character as the output label.
I am ...
2
votes
1
answer
473
views
Validation loss is less than training loss by 5 units. How this result is interpreted?
Iam training a Keras model for end-to-end speech recognition. I have my own dataset of speech containing about 400 wave files. Text transcriptions is also given as input. Model summary is:
...
4
votes
2
answers
11k
views
How to convert a mel spectrogram to log-scaled mel spectrogram
I was reading this paper on environmental noise discrimination using Convolution Neural Networks and wanted to reproduce their results. They convert WAV files into log-scaled mel spectrograms. How do ...
0
votes
1
answer
342
views
How can I create a space in IBM Cloud?
I want to try the IBM speech to text API. I created an IBM cloud account and went to https://console.bluemix.net/catalog/services/speech-to-text. I see the error message:
Please create a space in ...