Sphinx-4: a flexible open source framework for speech recognition
By William Walker, Paul Lamere, Philip Kwok, Bhiksha Raj, Rita Singh, Evandro Bacci Gouvêa, Peter Wolf, Joseph Woelfel. 2004
539 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/7d060fc04306580d8693e1335caf4c37ad83357b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Li Deng
- Dong Yu
- Mirco Ravanelli
- Daniel Povey
- Shinji Watanabe
- James R. Glass
- Kyunghyun Cho
Citations in the corpus
- Gyrophone: Recognizing Speech from Gyroscope Signals (2014, methodology): “We used Sphinx-4 [47] – a well-known open-source speech recognizer and trainer developed in Carnegie Mellon University.”
- PARTIES: QoS-Aware Resource Partitioning for Multiple Interactive Services (2019, background): “• Sphinx [54] is a speech recognition system with acoustic, phonetic, and language models, conigured as in [37].”
- The Kaldi Speech Recognition Toolkit (2011, background): “Notable among these are: HTK [1], Julius [2] (both written in C), Sphinx-4 [3] (written in Java), and the RWTH ASR toolkit [4] (written in C++).”
- Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems (2021, methodology): “The Spoken-SQuAD data set contains the audio form of the document that has been artificially constructed by using Google text-to-speech system, and then the textual form of the document was generated using the CMU Sphinx speech recognizer (Walker et al. 2004).”
- Optoelectronic Reservoir Computing (2011, methodology): “The Sphinx-4 system [31] uses a completely di erent method based on Hidden Markov Models and achieves a WER of 0.”
- RASR/NN: The RWTH neural network toolkit for speech recognition (2014, background): “Index Terms— speech recognition, acoustic modeling, neural networks, GPU, open source, RASR”
- Prosodic and temporal features for language modeling for dialog (2012, methodology): “Not having good acoustic models for English at hand, we tried it on the Verbmobil corpus, using the Sphinx-4 (Walker et al., 2004) recognizer with simple one-pass decoding without subsequent hypothesis re-ranking.”