Martin J. Russell

Learn More
“Segmental hidden Markov models” (SHMMs) are intended to overcome important speech-modelling limitations of the conventional-HMM approach by representing sequences (or segments) of features and incorporating the concept of trajectories to describe how features change over time. A novel feature of the approach presented in this paper is that extra-segmental(More)
Speech recognition is a computationally demanding task, particularly the stage which uses Viterbi decoding for converting pre-processed speech data into words or sub-word units. We present an FPGA implementations of the decoder based on continuous hidden Markov models (HMMs) representing monophones, and demonstrate that it can process speech 75 times real(More)
This paper deals with databases that combine different aspects: children’s speech, emotional speech, human-robot communication, crosslinguistics, and read vs. spontaneous speech: in a Wizard-of-Oz scenario, German and English children had to instruct Sony’s AIBO robot to fulfil specific tasks. In one experimental condition, strictly parallel for German and(More)
Previous studies have shown that children’s speech is more difficult to recognize by machine than adults’ speech. This paper presents the results of experiments which investigate recognition performance variation within a small population of children. Results suggest that recogniser performance on a child’s speech is well correlated with a teacher’s(More)
In real speaker verification applications, additive or convolutive noise creates a mismatch between training and recognition environments, degrading performance. Parallel Model Combination (PMC) is used successfully to improve the noise robustness of Hidden Markov Model (HMM) based speech recognisers [5]. This paper presents the results of applying PMC to(More)
The ABI (Accents of the British Isles) speech corpus contains approximately 90 hours of speech from approximately 280 speakers representing 14 different regional accents of British and Irish English. ABI includes a combination of applicationsoriented and linguistically-motivated material. This paper describes experiments in which the ABI corpus is used to(More)