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.

Filter by
Sorted by
Tagged with
0 votes
0 answers
14 views

equal error rate increasing while training speaker recognition model

I'm training a ResNet-based speaker recognition model. This is a fixed-data training protocol. I am validating my model on a different test set. The issue is the more I am training it seems the VEER ...
user avatar
0 votes
0 answers
37 views

speaker recognition: training on enrollment data

I'm working on a speaker recognition challenge. I have already trained my model on the voxceleb2 dataset in triplet setup. Now, for the challenge, I have two sets. enrollment (1 audio/subject) [IDs ...
user avatar
0 votes
0 answers
131 views

Practical calculation of EER (equal error rate) for biometric tasks

I am recently experimenting with the speaker recognition task. So, EER is calculated for a threshold FAR = FRR. Now, my question is how can I calculate this given I ...
user avatar
1 vote
0 answers
16 views

Hidden Markov models in Speech Recognition

My first question here. So I am trying to build a sign language translator(from signs to text) and noticed that the problem itself is quite similar to speech recognition, so I started to research ...
user avatar
0 votes
0 answers
25 views

Z-score or MinMax for pitch comparison?

I'm using the differences in pitch between two speakers as a feature in a random forest. Given that the corpus of conversations I am using are a combination of mixed and same-sex conversations, I wish ...
user avatar
  • 213
1 vote
0 answers
218 views

Why almost all neural speech processing involves Mel Spectrograms?

What are the reasons behind almost all speech processing whether it be generative or recognition heavily based on Mel Spectrograms? In a conversation with a signal processing expert I was asked why ...
user avatar
1 vote
0 answers
38 views

How to decode an output from a phoneme recognition model?

I created a phoneme recognition model (based on a pre-embedding with Wav2vec, and some layers on top of it) that takes as input an audio signal, and outputs a softmax matrix of size $N \times C$, ...
user avatar
0 votes
0 answers
21 views

CTC Speech Recognition Model giving absurd results on actual recording

I have trained a speech recognition model which uses CTCLoss and is inspired from https://www.assemblyai.com/blog/end-to-end-speech-recognition-pytorch I trained it on the Librispeech Dataset (train-...
user avatar
2 votes
0 answers
47 views

Confusion about the derivative in CTC

I was going through the original CTC paper by Graves et al, I am still not getting how after taking the derivative of equation 14 we get equation 15 as shown below I understand the part that we are ...
user avatar
0 votes
1 answer
57 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, ...
user avatar
0 votes
1 answer
162 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 ...
user avatar
  • 309
2 votes
1 answer
273 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 ...
user avatar
  • 309
1 vote
2 answers
276 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-...
user avatar
  • 309
0 votes
1 answer
125 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 ...
user avatar
1 vote
1 answer
236 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 ...
user avatar
  • 111
1 vote
0 answers
101 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 ...
user avatar
  • 161
0 votes
1 answer
52 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 ...
user avatar
0 votes
2 answers
176 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 ...
user avatar
2 votes
1 answer
79 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 ...
user avatar
  • 644
1 vote
1 answer
507 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, ...
user avatar
0 votes
1 answer
91 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? ...
user avatar
  • 115
2 votes
1 answer
162 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 ...
user avatar
1 vote
1 answer
2k 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. ...
user avatar
  • 113
2 votes
1 answer
101 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 ...
user avatar
1 vote
1 answer
26 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 ...
user avatar
  • 209
0 votes
1 answer
38 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 ...
user avatar
  • 103
1 vote
1 answer
208 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 ...
user avatar
2 votes
1 answer
76 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 ...
user avatar
  • 1,455
1 vote
0 answers
220 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?
user avatar
1 vote
1 answer
1k 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 ...
user avatar
  • 123
1 vote
1 answer
153 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 ...
user avatar
  • 223
1 vote
2 answers
2k 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 ...
user avatar
2 votes
1 answer
50 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 ...
user avatar
1 vote
0 answers
211 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" (...
user avatar
1 vote
1 answer
223 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 ...
user avatar
  • 13
0 votes
2 answers
516 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 ...
user avatar
  • 115
3 votes
0 answers
1k 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: ...
user avatar
0 votes
1 answer
100 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 ...
user avatar
7 votes
1 answer
4k 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 ...
user avatar
  • 56.4k
2 votes
1 answer
763 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 ($...
user avatar
  • 151
1 vote
1 answer
988 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: ...
user avatar
0 votes
1 answer
83 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 ...
user avatar
0 votes
1 answer
105 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 ...
user avatar
  • 179
0 votes
0 answers
568 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. "...
user avatar
  • 115
2 votes
1 answer
119 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 ...
user avatar
  • 131
0 votes
1 answer
52 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 ...
user avatar
  • 149
2 votes
2 answers
355 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 ...
user avatar
3 votes
0 answers
234 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 ...
user avatar
1 vote
1 answer
113 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 ...
user avatar
1 vote
1 answer
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 ...
user avatar
  • 555