Speech Recognition & Synthesis: Difference between revisions

Speech Services

Developer(s)	Google
Initial release	November 13, 2013; 10 years ago (2013-11-13)
Stable release	26.568.436572860.3 / April 9, 2022; 2 years ago (2022-04-09)[1]
Operating system	Android
Type	Screen reader

Speech Services^[2] is a screen reader application developed by Google for its Android operating system. It powers applications to read aloud (speak) the text on the screen with support for many languages. Text-to-Speech may be used by apps such as Google Play Books for reading books aloud, by Google Translate for reading aloud translations providing useful insight to the pronunciation of words, by Google TalkBack and other spoken feedback accessibility-based applications, as well as by third-party apps. Users must install voice data for each language.

Supported languages

History

This section relies largely or entirely on a single source. Relevant discussion may be found on the talk page. Please help improve this article by introducing citations to additional sources. Find sources: "Speech Recognition & Synthesis" – news · newspapers · books · scholar · JSTOR (March 2022)

Some app developers have started adapting and tweaking their Android Auto apps to include Text-to-Speech, such as Hyundai in 2015.^[3] Apps such as textPlus and WhatsApp use Text-to-Speech to read notifications aloud and provide voice-reply functionality.

Google Cloud Text-to-Speech is powered by WaveNet, software created by Google's UK-based AI subsidiary DeepMind, which was bought by Google in 2014. It tries to distinguish from its competitors, Amazon and Microsoft, with distinct AI features.

DeepMind's AI voice synthesis tech is notably advanced and realistic. Most voice synthesizers (including Apple's Siri) use concatenative synthesis, in which a program stores individual phonemes and then pieces them together to form words and sentences.

A WaveNet generates speech that sounds more natural than other text-to-speech systems. It synthesizes speech with more human-like emphasis and inflection on syllables, phonemes, and words. On average, a WaveNet produces speech audio that people prefer over other text-to-speech technologies. Unlike most other text-to-speech systems, a WaveNet model creates raw audio waveforms from scratch. The model uses a neural network that has been trained using a large volume of speech samples. During training, the network extracts the underlying structure of the speech, such as which tones follow each other and what a realistic speech waveform looks like. When given a text input, the trained WaveNet model can generate the corresponding speech waveforms from scratch, one sample at a time, with up to 24,000 samples per second and seamless transitions between the individual sounds.

See also

• Speech synthesis
• VoiceOver
• Live Transcribe

References

External links

• Speech Recognition & Synthesis on Google Play