In Listen, Attend, and Spell (LAS) training, teacher forcing is typically used to force the decoder history to be the correct gold target $$y_i$$ instead of the model's prediction $$\hat{y}_i$$. Alternatively, a mixture of gold and decoder outputs can be utilized, such as selecting the gold output with 90% probability and the decoder prediction with 10% probability.

Teacher Forcing in Listen, Attend, and Spell Training

Listen, Attend, and Spell (LAS) encoder-decoder models for speech are trained using standard cross-entropy loss, similar to conditional language models. At decoding timestep $$i$$, the loss is evaluated as the negative log probability of the correct target token (which is typically a letter), denoted as $$y_i$$.

Columbia University

Google

The standard encoder-decoder architecture is which is generally called the attention-based encoder decoder or AED, or listen attend and spell (LAS). The standard encoder decoder architecture for ASR is sketched by the following image, which contains the schematic architecture for an encoder-decoder speech recognizer. 

Listen attend and spell (LAS)


An on-going but a helpful book resource about NLP
https://web.stanford.edu/~jurafsky/slp3/

Speech and Language Processing (3rd ed. draft) 

The encoder-decoder architecture is very appropriate when input and output sequences have significant difference in length, and they do for speech, since long acoustic feature sequences tend to map to much shorter sequences of letters or words. For example, a single word might be 5 letters long, but if it is spoken for 2 seconds, it would take 200 acoustic frames of 10 milliseconds each to map to. Due to this extreme length difference in speech, the encoder-decoder architectures for speech require a special compression stage that shortens the acoustic feature sequence before the stage of encoding. An alternative to this is using a loss function that deals with compression, like the CTC or connectionist temporal classification loss function.

Compression in LAS

An encoder-decoder model is basically a conditional language model, so encoder-decoders implicitly must learn a language model for the output domain of letters from training data. However, the training data, which is generally speech paired with text transcriptions, may not include as much text as you need to train a good language model, since it’s easier to find large amounts of pure text training data than it is to find text paired with speech. Therefore, a model for ASR can usually be improved by incorporating a very large language model. 

Adding a language model

After the compression stage, encoder-decoders for speech use either RNNs (LSTMs) or Transformers.

LAS Output

The input to a Listen, Attend, and Spell (LAS) model is a sequence of $$t$$ acoustic feature vectors $$F = f_1, f_2, \dots, f_t$$, where each vector spans a frame of 10 milliseconds. Assuming the output consists of letters, the output sequence is $$Y = (\langle SOS \rangle, y_1, \dots, y_m, \langle EOS \rangle)$$, where $$\langle SOS \rangle$$ is a special start-of-speech token and $$\langle EOS \rangle$$ is a special end-of-speech token. The associated image shows the character set often selected for the English language.

Learn Before

Related

Learn After