Details and Options

• Speech recognition aims to convert a spoken audio signal to text. It is also known as speech-to-text and is typically used in voice-enabled human-machine interactions and digital personal assistants.
• SpeechRecognize[audio] returns all recognized speech in audio as a single string.

• The following options can be given:
• Masking Allinterval of interest Method Automaticthe method to use TargetDevice"CPU"the device on which to perform recognition
• By default, speech in the whole signal is recognized. Use Masking->{int₁,int₂,…} to limit the recognition to intervals int_i.
• Possible settings for Method are:
• "GoogleSpeech"uses Google speech-to-text "NeuralNetwork"uses built-in neural networks "OpenAI"uses the OpenAI speech-to-text
• SpeechRecognize only works for English speech.
• SpeechRecognize uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
• SpeechRecognize may download resources that will be stored in your local object store at $LocalBase, and can be listed using LocalObjects[] and removed using ResourceRemove.

Examples

Basic Examples  (2)

Recognize speech in an audio signal:

Recognize speech from a recording:

Options  (2)

Masking  (1)

Use the Masking option to recognize parts of a signal:

Method  (1)

By default, a local model is used for speech recognition:

Use OpenAI speech recognition:

Use GoogleSpeech speech recognition:

Applications  (4)

Use AudioIntervals to select which parts of the signal to recognize:

Interpret a spoken city:

Show the recognized city on the map:

Find the answer from a spoken question in a text:

Build an automatic assistant based on Wolfram|Alpha: