Preprint
Sequence Transduction with Recurrent Neural Networks
Alex Graves, arXiv (ICML 2012 Workshop on Representation Learning), 2012
Read the originalRead on October 16, 2026
- What it is
- The paper that introduced the RNN transducer, an end-to-end system that learns both the alignment between audio and text and the output sequence. It reports phoneme recognition on the TIMIT corpus.
- How much weight it carries
- Foundational paper by the inventor of the method, published at an ICML workshop. It is a technical description with a small experiment, not a modern accuracy benchmark.
Facts taken from this source
- Graves wrote in 2012 that recurrent networks traditionally required a pre-defined alignment between input and output sequences, and introduced an end-to-end transduction system that removes that need.
“RNNs traditionally require a pre-defined alignment between the input and output sequences to perform transduction.” (Abstract)
Pages that rest on this source
- Speech Recognition: What It Is and How Well It WorksTopic
- How Speech Recognition Works, From Sound to TextGuide
- Speech Recognition Models: How Neural ASR WorksGuide
- Real-Time Speech Recognition: Streaming and LatencyGuide
- History of Speech Recognition: From Audrey to WhisperGuide
- What role do hidden Markov models play in speech recognition?Question
- RNN transducer (RNN-T)Glossary