Identifying user-defined keywords is crucial for personalizing interactions
with smart devices. Previous approaches of user-defined keyword spotting
(UDKWS) have relied on short-term spectral features such as mel frequency
cepstral coefficients (MFCC) to detect the spoken keyword. However, these
features may face challenges in accurately identifying closely related
pronunciation of audio-text pairs, due to their limited capability in capturing
the temporal dynamics of the speech signal. To address this challenge, we
propose to use shifted delta coefficients (SDC) which help in capturing
pronunciation variability (transition between connecting phonemes) by
incorporating long-term temporal information. The performance of the SDC
feature is compared with various baseline features across four different
datasets using a cross-attention based end-to-end system. Additionally, various
configurations of SDC are explored to find the suitable temporal context for
the UDKWS task. The experimental results reveal that the SDC feature
outperforms the MFCC baseline feature, exhibiting an improvement of 8.32% in
area under the curve (AUC) and 8.69% in terms of equal error rate (EER) on the
challenging Libriphrase-hard dataset. Moreover, the proposed approach
demonstrated superior performance when compared to state-of-the-art UDKWS
techniques.

通过使用移位增量系数（SDC）捕捉发音变异性并结合长时信息，该研究表明，SDC 特征相对于短时谱特征（如 MFCC）在用户定义关键词识别任务中取得了更好的表现，其 AUC 指标提高了 8.32%，等错误率（EER）降低了 8.69%。

使用偏移增量系数的端到端用户定义关键词检测

End-to-End User-Defined Keyword Spotting using Shifted Delta  Coefficients

Analysis of Indian English (IE) pronunciation variabilities are useful in
building systems for Automatic Speech Recognition (ASR) and Text-to-Speech
(TTS) synthesis in the Indian context. Typically, these pronunciation
variabilities have been explored by comparing IE pronunciation with Received
Pronunciation (RP). However, to explore these variabilities, it is required to
have labelled pronunciation data at the phonetic level, which is scarce for IE.
Moreover, versatility of IE stems from the influence of a large diversity of
the speakers' mother tongues and demographic region differences. Prior
linguistic works have characterised features of IE variabilities qualitatively
by reporting phonetic rules that represent such variations relative to RP. The
qualitative descriptions often lack quantitative descriptors and data-driven
analysis of diverse IE pronunciation data to characterise IE on the phonetic
level. To address these issues, in this work, we consider a corpus, Indic
TIMIT, containing a large set of IE varieties from 80 speakers from various
regions of India. We present an analysis to obtain the new set of phonetic
rules representing IE pronunciation variabilities relative to RP in a
data-driven manner. We do this using 15,974 phonetic transcriptions, of which
13,632 were obtained manually in addition to those part of the corpus.
Furthermore, we validate the rules obtained from the analysis against the
existing phonetic rules to identify the relevance of the obtained phonetic
rules and test the efficacy of Grapheme-to-Phoneme (G2P) conversion developed
based on the obtained rules considering Phoneme Error Rate (PER) as the metric
for performance.

本文从语音识别和语音合成的角度出发，对印度英语的发音变异进行了分析和研究，提出了一种基于数据驱动的新型语音转换模型，并用基于音素错误率的性能指标进行了测试。