Questions tagged [speech-recognition]
Automatic speech recognition (ASR) aims to identify words and phrases in spoken language and convert them to a machine-readable format.
50
questions
0
votes
1answer
20 views
Speech recognition (SVM) different signal lengths
I am developing a small project on speech recognition, the idea is to classify sound sources by Support Vector Machines. My dataset consists on 45 signals, however, they all have different lengths, ...
0
votes
1answer
63 views
Why does one need Google's WaveNet model to generate audio if it already takes audio as input?
I've spent a lot of time trying to understand the Google's WaveNet work (also used in their DeepVoice model), but still confused about some very basic aspects. I'm referring to this Tensorflow ...
1
vote
1answer
30 views
Mismatching dimensions of input/output in the WaveNet model for text-to-speech generation?
I have been trying to understand the model of how speech generation works, particularly in WaveNet model by Google. I was referring to the original WaveNet paper and this implementation:
I find the ...
0
votes
0answers
15 views
How to understand the dilated conv1d layers dimensions in this model?
I was trying to see the layers used in a Wavenet model for speech generation and I can't seem to make sense of the output layers printed by the TF model. Model is this: https://github.com/Rayhane-...
1
vote
1answer
31 views
How are text-to-speech systems' spectrogram frames aligned for loss calculation?
A key aspect of how text-to-speech (TTS) machine-learning works is very unclear to me even after reading the Tacotron-2 paper and the Google AI blog.
https://ai.googleblog.com/2017/12/tacotron-2-...
0
votes
0answers
12 views
how many spectogram frames per input character does text-to-speech (TTS) system Tacotron-2 generate?
I've been reading on Tacotron-2, a text-to-speech system, that generates speech just-like humans (indistinguisahble from humans) using the github https://github.com/Rayhane-mamah/Tacotron-2.
I'm very ...
0
votes
0answers
7 views
Speech recognition,Voice activity detection
In a video, or a movie, there may be a section that depicts the environment or the scene. In these clips, there is no normal dialogue between the characters. At this time, the audio track of the video ...
0
votes
1answer
19 views
Aggregating LSTM subsequence output into full sequence
I have an n->n seq2seq LSTM that takes a sequence of length n and produces a sequence of length ...
1
vote
1answer
25 views
Speaker Recognition ML tasks are supervised or unsupervised?
Given the scenario:
We have a speech recording from an unknown person.
We have a speech recording from a known person.
We have a large database of speech recordings from different persons.
We would ...
1
vote
0answers
34 views
Question about Connectionist Temporal Classification (CTC) gradient
I have read the original CTC paper by Graves et al, but am confused about equation 16, for which the authors derive the gradient of the negative log likelihood objective with respect to the inputs of ...
0
votes
0answers
34 views
What are linguistic features and fundamental frequency in WaveNet? How are they obtained from trained model?
WaveNets for the TTS task were locally conditioned on linguistic features which were derived
from input texts. We also trained WaveNets conditioned on the logarithmic fundamental frequency
$(logF_{...
0
votes
0answers
10 views
Neural network converges to bias in high multi-label scenario
I am trying to create a trigger word detection system by following the tutorial:
https://github.com/Kulbear/deep-learning-coursera/blob/master/Sequence%20Models/Trigger%20word%20detection%20-%20v1....
0
votes
1answer
38 views
Interpolating speech from different speakers in trigger word detection
Trigger word detection aims to essentially identify the timestamp of a "trigger word" occurring in a chunk of audio. The approaches I have seen online, in particular, following along with Andrew Ng's ...
0
votes
2answers
81 views
Does speech recognition model training require transcript timestamps
I don't quite understand how a recurrent neural network or LSTM is trained for automatic speech transcription. Say I have n audio files of speech, each with an ...
1
vote
1answer
32 views
Method for detecting previously unseen class
Is there any common practice for detecting a new class, or data associated with an previously unseen event?
I'm doing some research into speech recognition, and I'm trying to detect when a speech ...
0
votes
0answers
23 views
Representing and Training Individualized Models
Say I want to create a handwriting OCR or speech-to-text system intended for many users. A first pass might be to train a single one-size-fits-all model on all available data to predict all users' ...
1
vote
0answers
171 views
Number of parameters of tacotron, deep voice, wavenet?
I have recently started to explore speech synthesis, and started reading some paper. I have implemented a dummy text to speech synthesis model too, it has around 92 million parameters.
Even though, ...
0
votes
1answer
39 views
k-means clustering issue voice data
I'm getting an issue in my k-means I don't know if it my data-set or what anything else.
Why i got thia flowing point in the right side of the image?
...
2
votes
1answer
82 views
When use CTC-loss for speech recognition?
I'm trying to understand and implement CTC-loss for speech recognition (here on SO). I'll like to have more information about the use cases of this technique.
From what i understood, it is more ...
1
vote
1answer
439 views
How do you evaluate/test accuracy of Text-to-Speech (TTS) models?
As the title implies...
For instance, for Machine Translation, we have BLEU.
For categorization, we have categorical crossentropy, for binary categorization, we have binary crossentropy, etc. etc.
...
2
votes
1answer
52 views
Streaming audio to neural network
I am trying to create a neural network that performs speaker recognition. I would like to be able to serve it such that it takes streaming audio - i.e. I want to perform partial recognition on 100ms ...
1
vote
1answer
18 views
Is there a keyword recognition system without learning the Phoneme
As I understand in speech processing and machine learning area "keyword recognition" (also termed as keyword spotting) is a important part. In "keyword recognition" sytem it is desired to learn a ...
0
votes
1answer
30 views
Deciding length of units in sound recognition for training HMMs
I am working on creating a method to detect changes from one song to another. Namely, I hope to use a Hidden Markov Model (HMM) in order to model a part of a song and check to see if it accurately ...
1
vote
1answer
119 views
Are e2e DL systems better than DNN-HMM models in speech recognition?
End-to-end deep learning systems for automatic speech recognition (ASR) have been around for a while now since Deep Speech (2014), but I noticed that DNN-HMM based methods are still performing well ...
2
votes
1answer
50 views
How to use GMMs for acoustic signal classification?
There are a number of applications of the Gaussian Mixture Model (GMMs) to acoustics/audio data for the purposes of classification; ex paper1 and ex paper2. GMMs ...
1
vote
0answers
190 views
How to create dataset for speech recognition using librosa [closed]
I loaded the audio using librosa and extracted mfcc feature of the audio. I now have array of shape (20,N). How do I feed this as input to LSTM to predict?
1
vote
1answer
663 views
WaveNet Global and local conditioning
WaveNet is a deep learning framework able to generate raw audio signal from a sequence like text sequence.
https://arxiv.org/abs/1609.03499
It is also possible to "imitate" in a way the voice of the ...
1
vote
1answer
79 views
Speech recognition - hangover scheme - voice activity detection
I am doing a voice activity detection challenge, and I am asked to add a hangover scheme to the model. I read about hangover schemes in different papers but I couldn't find a definition for this. What ...
1
vote
2answers
970 views
What is low rank linear layer in neural networks?
Going through the paper Convolutional Neural Network for Small-footprint Keyword Spotting. In the paper, authors have used low rank linear layer after convolution ...
2
votes
1answer
48 views
Verifying Time Warp
Time warp has been widely assumed in domain of speech processing. If $Xw(t)$ represents a time warped version of $X(t)$, then $Xw(t) = X(t-w(t))$ where $w(t)$ is an arbitrary function with a banded ...
1
vote
0answers
168 views
How does CTC work in Speech Recognition?
I have already read the 2006 Paper about CTC by Graves but I still don't understand it fully. I am searching for a simple but still detailed explanation of how "Connectionist Temporal Classification" (...
1
vote
1answer
147 views
RNN(LSTM) model fails to classify new speaker voice
I'm fairly new to ML and at the moment I'm trying to develop a model that can classify spoken digits (0-9) by extracting mfcc features from audio files.
My data ...
0
votes
1answer
449 views
Transfer learning for audio
I know that when working with images, what people normally do is download a big model trained with huge data and freeze most of the layers except the lasts ones to train them with their own data.
I'm ...
3
votes
0answers
977 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:
...
0
votes
1answer
93 views
Adapt speech recognition for Shakespeare english
We need to be able to search the works of Shakespeare by voice. The way I see it, the goal is if I quote into the microphone:
"Yet but three come one more.
Two of both kinds make up four.
Ere ...
7
votes
1answer
3k views
Turkish speech recognition (speech->text) in Google Speech API? [closed]
Google's Speech API has audio speech to text capabilities in multiple languages. It supports Turkish too. That language is very interesting, it's so called agglutinative: you stick word parts one ...
1
vote
1answer
354 views
Word Error Rate over Data Set
In speech to text, one common metric is the word error rate (WER).
WER is the word-level Levenshtein distance, which is the minimum number of substitutions ($S$), deletions ($D$), and insertions ($...
1
vote
1answer
611 views
How to normalize text when computing the word error rate of a speech recognition system?
I am looking for a library, script or program that can normalize the transcribed and gold texts when computing the word error rate (WER) of an automated speech recognition system.
For example, if:
...
0
votes
1answer
77 views
Spot word in spoken sentence : advice needed
I have to make a live speech recognition program that can spot specific words in a spoken sentence. For now I have to recognize the words "yes" and "no".
I already trained Google's model and it ...
0
votes
1answer
93 views
How to prevent the creation of redundant mixtures while training a GMM?
I'm currently trying to train a GMM(UBM) with 1024 Gaussian mixtures for speaker verification.
However, after training the GMM, it appears that some mixtures are useless/redundant.
(little to no ...
0
votes
0answers
533 views
Keyword Spotting: How to train a model with general speech corpus?
I am trying to find a correct way to train a DNN based keyword spotting (Deep KWS) with general speech corpus (VS data) described in this paper (Chen, Guoguo, Carolina Parada, and Georg Heigold. "...
2
votes
1answer
96 views
MFCCs and MoG-HMMs for speech recognition
BACKGROUND
MFCCs are coefficients which represent the most important parts of speech, and about 12 of them are used to model a one 512 points long frame (of speech). Along with them you would use ...
0
votes
1answer
50 views
Why is phase reconstruction considered hard
I am studying deep learning models for single channel speech separation.
I come across several recent methods:
Permutation Invariant Training
Deep Clustering
Deep Attractor Network
All of these ...
2
votes
2answers
333 views
Why has deep learning only shown decent results in the fields of computer vision and speech recognition? [closed]
We all know about the success of ImageNet, AlphaGo etc which used deep neural networks in computer vision, or the use of RNNs in Google Translate. But why are we not seeing similar advances in other ...
3
votes
0answers
229 views
Program to evaluate the output of a speech recognition system
I am looking for a library, script or program that can evaluate the output of a speech recognition system. The output of the speech recognition system is a simple text file, and I have the gold output ...
0
votes
1answer
100 views
how we input speech signal waveforms in two deep learning algorithms?
I am working with deep learning algorithms like CNN and RNN.I always wonder what is the best way to input wave form type data in to the deep learning algo. I know there are methods like wavelet or mel ...
0
votes
1answer
1k views
Forced alignment HMM
I am currently trying to understand what is involved to train a Hidden Markov Model (HMM) with Forced alignment. Forced alignment, as far I understand, is to align the audio file with the utterance ...
1
vote
1answer
709 views
Understanding hidden markov model, and how it is applied in speech recognition
I have for some some time tried to understand how this hidden markov model (hmm) works, and have found a lot of tutorials/papers on it which make use of the same examples/principles of explaining the ...
1
vote
1answer
961 views
How to derive the GMM log-likelihood formulation in the eigenvoice modeling technique?
Given a GMM with mean $M=[M_1, M_2, ..., M_C]$ and covariance $\Sigma=[\Sigma_1, \Sigma_2, ..., \Sigma_C]$ (where $C$ is the number of mixtures),
many papers on eigenvoice modeling states that the ...
3
votes
0answers
679 views
The state-of-the-art methods for speech recognition?
Recently I noticed that Google and Apple have really high quality speech-recognition services. I was wondering about the state-of-the-art methods and techniques they are/might be using to achieve such ...
