This research studies the Projected Bidirectional Long Short-Term Memory Time Delayed Neural Network (TDNN-BLSTM) model for English phoneme recognition. It contributes to the field of phoneme recognition by analyzing the performance of the TDNN-BLSTM model based on the TIMIT corpus and the Buckeye corpus, respectively containing read speech and spontaneous speech. The TIMIT corpus can be used as benchmark to make comparisons between architectures. The Buckeye corpus is used to better understand how the TDNN-BLSTM architecture would perform on recorded informal conversations.
Parameter values are taken from literature and are optimized.
Using the improved parameters, the results show Phoneme Error Rates (PER) for read speech to be 31.78% and for spontaneous speech to be 54.03%. Related work shows PER scores for read speech to be 14.9% and for spontaneous speech to be 23.4%.
This indicates that the TDNN-BLSTM architecture does not perform as well as other acoustic models for both spontaneous and read speech.

Automatic phoneme recognition (APR) is the process of recognizing phonemes (spoken sounds) in a recording of speech. It can be used for any application requiring fast and accurate transcription, i.e. a courthouse. This research creates such a model using the TDNN-OPGRU architecture and trains it on two datasets of recorded English speech - "TIMIT" for prewritten sentences being read out (prepared/read speech) and "Buckeye" for recorded interviews (spontaneous speech). The results of the model are analyzed and compared to similar research. The main conclusion is that the results obtained do not exceed previous research and in some cases are considerably worse. The reasoning for that is also included.

A limitation of current ASR systems is the so-called out-of-vocabulary words. The solution to overcome this limitation is to use APR systems. Previous research on Dutch APR systems identified Time Delayed Bidirectional Long-Short Term Memory Neural Network (TDNN-BLSTM) as one of best performing state-of-the-art NN architecture for PR. The goal of this research is to evaluate the performance of the TDNN-BLSTM architecture for phoneme recognition on Mandarin read and spontaneous speech, analyze the differences in performance for the two speech styles as well as compare the results with previous research on Dutch PR.

To achieve this goal 4 different NN models of the TDNN-BLSTM architecture were built and trained on Mandarin read and spontaneous speech. The test results of the NN models were used to calculate the phoneme error rate (PER), decomposed PER, and the contribution of individual phonemes to the overall PER. Based on these findings, conclusions are formulated regarding the impact of different languages, speech styles, and the architectural changes on the performance of the TDNN-BLSTM architecture.

This research expands past research on implementing the TDNN-OPGRU network for Automatic Phoneme Recognition on Dutch speech by implementing and testing the TDNN-OPGRU network on Mandarin speech. The goal of this research is to investigate the performance of the TDNN-OPGRU architecture when decoding phonemes in Mandarin prepared and spontaneous speech. The difference in Phoneme Error Rate between prepared and spontaneous speech is being determined, and the effect that tones have on the PER is being investigated since Mandarin is a tonal language. The results are that a substantial amount of the PER comes from substitutions that are made where only the tone is incorrectly determined. However, tone does not appear to have an impact on the difference in PER between spontaneous and prepared speech since it is responsible for an similar amount of the substitutions in both types of speech. The inclusion of tone also causes the error rate of the TDNN-OPGRU architecture on base phonemes to increase.