Speech is a basic mode of communication between us and most natural efficient form of exchanging information. Speech Recognition is a conversion of an acoustic waveform to text. Speech can be isolated, connected and continuous type. The goal of this work is to recognize a Continuous Speech using Mel Frequency Cepstrum Coefficients (MFCC) to extract the features of Speech signal, Hidden Markov Models (HMM) for pattern recognition and Viterbi Decoder for decoding of speech signal. Continuous Speech files of the TIMIT standard database are used for the work. The recognition success rate is calculated for the entire database, separate Training and Testing files are found in the database and we also prepared a small set of database used in our work. For the complete process we used Hidden Markov Model Tool Kit (HTK) which is an Open source tool developed by Cambridge University Engineering Department (CUED), which contains a set of standard C Programs for feature extraction, model building and for decoding purposes, for the entire work Linux Operating System fedora is used, The objective of the work is to develop an open source HTK based Continuous Speech Recognition & to obtain better recognition accuracy for large vocabulary size.

Background: Total knee replacement (TKR) is a commonly performed surgical procedure, all across the world. TKR may be associated with severe postoperative pain, usually requiring prolonged hospital stay and relative immobilization of the patient, may cause unwanted medical problems like nosocomial infections, DVT and poor surgical outcome. Local infiltration analgesia (LIA) is becoming more commonly used owing to the excellent pain relief, the low frequency of complications, and the antiinflammatory effect. The injection usually contains a mixture of an anesthetic drug and a NSAID, to which epinephrine or a corticosteroid can be added. LIA is easy to use, relatively cheap, and many authors concluded that it reduces pain and opioid consumption. Objectives:1. To assess the pain relief postoperatively using visual analogue score (VAS). 2. To assess the knee range of movements (knee flexion and extensor lag) postoperatively. Methods and Methodology:This study is an observational clinical study, centered at a private hospital between March 2019 to October 2020. Data was collected from 42 patients undergoing total knee replacement with local infiltration analgesia between the periods from March 2019 to 2020 October. Written and informed consent was taken. Patients with allergy to any of the study drugs, uncontrolled diabetes and hypertension were excluded from the study. A local infiltration injection of a mixture (cocktail) of drugs ropivacaine, ketorolac, adrenaline and normal saline was given using spinal needle. Quality of analgesia was estimated by using visual analogue score of 0 to 10 at 6 hr, 24hr, 48 hr, and 72hr after surgery during the rest and movement and knee range of movements was assessed postoperatively using goniometer. Data was collected and entered in excel sheet and was analyzed using paired t test. Software SPSS 20 was used for the statistical analysis. A P value of <0.001% was considered significant. Results: A total of 42 patients with Osteoarthritis knee undergoing TKR with LIA were included in the study. A local infiltration injection of a mixture (cocktail) of drugs listed above was given before and after the implantation of the components. VAS, KF and EL was measured postoperatively at 6hrs, 24hrs, 48 hrs, 72 hrs respectively. Our results showed that postoperative VAS was significantly better till 48 hours postoperatively. KF improved significantly postoperatively. There was improvement in the extensor lag from postoperative day three.