Speech recognition

How do machines understand our spoken words?

Imagine you're asking your smart home assistant to play your favorite song. You say, "Play 'Bohemian Rhapsody' by Queen," and it starts playing without asking for more details.

The assistant understands your request by recognizing the words you speak and translating them into text commands it can follow.

Example

When you say "Play 'Bohemian Rhapsody' by Queen," the system identifies the song title and artist, then searches its database to find and play the song.

Remember this

The hidden Markov model (HMM) helps the system predict and recognize speech patterns, making it possible to understand and execute your spoken commands.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

word error rate (WER) measures: edit distance between predicted and reference transcriptions

Ever wondered how machines understand speech as we do?

weight tying does in language models: shares embedding and output projection matrices

Ever wonder how machines understand the sequence of words in a sentence?

ring attention does: distributes long sequences across multiple devices

How can a machine understand and generate human language?

Prompt engineering

The GenAI model learns tasks from examples in the prompt

Machine learning in bioinformatics

How do Transformers understand what's important in a sentence?

QLoRA adds

Ever wondered how computers can understand and mimic human speech?

Swipe through 100 ML concepts daily

Open Pocket Polymath