Effect of Speaking Style on LVCSR Performance

By M. Weintraub, Kelsey Taussig, Kate Hunicke-Smith, Amy Snodgrass. 1996

Subfields: Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

1. Ne Luo
2. Wubo Li
3. Xiangang Li
4. Wei Zou
5. Dongwei Jiang
6. Mari Ostendorf
7. Stéphane Dupont
8. Izhak Shafran

Citations in the corpus

• Improving Transformer-based Speech Recognition Using Unsupervised Pre-training (2019, background): “Speaking style has a strong impact on performance of ASR systems [26, 27].”
• A Further Study of Unsupervised Pretraining for Transformer Based Speech Recognition (2020, background): “• The speaking style has a strong impact on the performance of ASR systems [18, 19].”
• PROSODY MODELS FOR CONVERSATIONAL SPEECH RECOGNITION (2003, background): “Conversational speech contains a large amount of prosodic variation, which seem to co-occur with greater acoustic variability more generally [4].”
• Automatic speech recognition and speech variability: A review (2007, methodology): “An appealing methodology has been proposed in Weintraub et al. (1996), where a comparison of ASR accuracy on the original Switchboard test data and on a reread version of it is proposed.”